{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":112509,"databundleVersionId":14254895,"sourceType":"competition"},{"sourceId":293691576,"sourceType":"kernelVersion"},{"sourceId":268942,"sourceType":"modelInstanceVersion","modelInstanceId":230141,"modelId":251887},{"sourceId":711299,"sourceType":"modelInstanceVersion","modelInstanceId":540408,"modelId":553604},{"sourceId":719660,"sourceType":"modelInstanceVersion","modelInstanceId":547330,"modelId":560139}],"dockerImageVersionId":31236,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true},"papermill":{"default_parameters":{},"duration":441.06159,"end_time":"2026-01-05T05:15:36.197688","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2026-01-05T05:08:15.136098","version":"2.6.0"},"widgets":{"application/vnd.jupyter.widget-state+json":{"state":{"5cea4344fed44fffaac71b6fe02ac50b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"5fd6570613f943ecb07631ffcecddacb":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"6b204ec19a394a818e17994aae3263e6":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"864a5d2d04374e688a854f72ad0d04d9":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"8f988be66966496085d6e6b8909bf0da":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_864a5d2d04374e688a854f72ad0d04d9","placeholder":"​","style":"IPY_MODEL_5cea4344fed44fffaac71b6fe02ac50b","tabbable":null,"tooltip":null,"value":" 1/1 [00:01<00:00,  1.98s/it]"}},"9a1a60c1824e4af4a02be7dd08d54449":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"af818733f9ec4e22a3500a5692c607b2":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_e8a7fcf1682642f9a95f077413387b58","IPY_MODEL_d548382ab4904dd9b1c2742bec3463f0","IPY_MODEL_8f988be66966496085d6e6b8909bf0da"],"layout":"IPY_MODEL_5fd6570613f943ecb07631ffcecddacb","tabbable":null,"tooltip":null}},"b695855014a24a7184902662cc419d1e":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d372dd276f534b6ba203146ce2f78865":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"d548382ab4904dd9b1c2742bec3463f0":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"ProgressView","bar_style":"success","description":"","description_allow_html":false,"layout":"IPY_MODEL_9a1a60c1824e4af4a02be7dd08d54449","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_d372dd276f534b6ba203146ce2f78865","tabbable":null,"tooltip":null,"value":1}},"e8a7fcf1682642f9a95f077413387b58":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_b695855014a24a7184902662cc419d1e","placeholder":"​","style":"IPY_MODEL_6b204ec19a394a818e17994aae3263e6","tabbable":null,"tooltip":null,"value":"100%"}}},"version_major":2,"version_minor":0}}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Thanks,\n\n## Credits: Eng Adam Al mohammedi, Baidalin, Adilzhan, CigarCat, Mattia Angeli, Khoa, samu2505 \n\n## siglep LB: 65 now: -\n\n## dinov3 Lb: 70 now: +","metadata":{}},{"cell_type":"markdown","source":"16m 23s · GPU P100\nOOF・early_stopping_rounds・FORCE_CLOVER_ZERO: bool の設定追加\n1) CatBoost：低学習率 × 多反復 + 正則化強化\n具体設定（試す順）\n\nlearning_rate: 0.045 → 0.02（試行レンジ 0.01–0.03）\n\niterations: 1900 → 3000–4000（early_stopping_rounds=200 を有効化）\n\nl2_leaf_reg: 0.56 → 1.0–2.0\n\nbagging_temperature: 現状 0.98 のままか 0.5–1.2 を試す\n\n理由\n\n現状 CatBoost の fold スコアは比較的良いが分散がやや大きい（std ≈ 0.018）。低 LR × 多反復は学習の安定化と汎化改善に効きやすく、L2 を増やすことで過学習を抑制できる。\n\n期待効果\n\nOOF の分散低下、fold 間の安定化、最終アンサンブルでの寄与向上（Public/Private ギャップ縮小）。\n\n検証方法\n\nまず 1 fold（短時間）で lr を 0.03, 0.02, 0.01 で比較。各設定で fold の val 加重R² と学習曲線（train/val loss）を確認。最良設定を 5-fold で再検証。\n3. 埋め込み変換とセマンティック処理の改善（中期）\nPCA/PLS/GMM の感度試験\n\n優先候補（1fold で試す）：\n\nA: PCA=0.95, PLS=12, GMM=8\n\nB: PCA=0.90, PLS=10, GMM=6\n\nC: 現状 PCA=0.99, PLS=12, GMM=8（ベース）\n\n指標：1fold の weighted R²、特徴次元数、学習時間。良ければ 5-fold 実行。\n\nSemantic 正規化を robust に\n\n現在の z-score を (x - median)/IQR に変更し clip(-5,5) を適用。外れ値に強くなり GBM 系の安定化に寄与する。\n\n特徴選択の検討\n\nPCA 後の説明分散が低い成分を除外する、または L1 ベースの簡易選択を試す。","metadata":{}},{"cell_type":"code","source":"import os\nimport gc\nimport random\nimport warnings\nimport numpy as np\nimport pandas as pd\nimport cv2\nimport torch\nfrom PIL import Image\nfrom tqdm.auto import tqdm\nfrom pathlib import Path\nfrom copy import deepcopy\nfrom dataclasses import dataclass\nimport lightgbm as lgb\n\n# Sklearn & Models\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.decomposition import PCA\nfrom sklearn.cross_decomposition import PLSRegression\nfrom sklearn.mixture import GaussianMixture\nfrom sklearn.ensemble import GradientBoostingRegressor, HistGradientBoostingRegressor\nfrom lightgbm import LGBMRegressor\nfrom catboost import CatBoostRegressor\nfrom transformers import AutoModel, AutoImageProcessor, AutoTokenizer\n\n# Suppress warnings\nwarnings.filterwarnings('ignore')\nos.environ[\"TOKENIZERS_PARALLELISM\"] = \"false\"\n\n# =========================================================================================\n# 1. CONFIGURATION & SEEDING\n# =========================================================================================\n@dataclass\nclass Config:\n DATA_PATH: Path = Path(\"/kaggle/input/csiro-biomass/\")\n SPLIT_PATH: Path = Path(\"/kaggle/input/csiro-datasplit/csiro_data_split.csv\")\n SIGLIP_PATH: str = \"/kaggle/input/google-siglip-so400m-patch14-384/transformers/default/1\"\n \n SEED: int = 42\n DEVICE: str = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n PATCH_SIZE: int = 520\n OVERLAP: int = 16\n \n # Target definitions\n TARGET_NAMES = ['Dry_Clover_g', 'Dry_Dead_g', 'Dry_Green_g', 'Dry_Total_g', 'GDM_g']\n TARGET_MAX = {\n \"Dry_Clover_g\": 71.7865,\n \"Dry_Dead_g\": 83.8407,\n \"Dry_Green_g\": 157.9836,\n \"Dry_Total_g\": 185.70,\n \"GDM_g\": 157.9836,\n }\n # cfg.TARGET_NAMES の順に合わせた重み（必ずこの順で設定）\n R2_WEIGHTS: list = (0.1, 0.1, 0.1, 0.5, 0.2)\n\n # 追加（デフォルトは True：従来の挙動:0固定）\n FORCE_CLOVER_ZERO: bool = True\n\n\ncfg = Config()\n\ndef seeding(SEED):\n np.random.seed(SEED)\n random.seed(SEED)\n os.environ['PYTHONHASHSEED'] = str(SEED)\n torch.manual_seed(SEED)\n if torch.cuda.is_available(): \n torch.cuda.manual_seed(SEED)\n torch.backends.cudnn.deterministic = True\n torch.backends.cudnn.benchmark = False\n\nseeding(cfg.SEED)\n\n# =========================================================================================\n# 2. DATA LOADING & PRE-PROCESSING\n# =========================================================================================\ndef pivot_table(df: pd.DataFrame) -> pd.DataFrame:\n if 'target' in df.columns.tolist():\n # Train data\n df_pt = pd.pivot_table(\n df, \n values='target', \n index=['image_path', 'Sampling_Date', 'State', 'Species', 'Pre_GSHH_NDVI', 'Height_Ave_cm'], \n columns='target_name', \n aggfunc='mean'\n ).reset_index()\n else:\n # Test data\n df['target'] = 0\n df_pt = pd.pivot_table(\n df, \n values='target', \n index='image_path', \n columns='target_name', \n aggfunc='mean'\n ).reset_index()\n return df_pt\n\ndef melt_table(df: pd.DataFrame) -> pd.DataFrame:\n melted = df.melt(\n id_vars='image_path',\n value_vars=cfg.TARGET_NAMES,\n var_name='target_name',\n value_name='target'\n )\n # Create sample_id matching submission format\n melted['sample_id'] = (\n melted['image_path']\n .str.replace(r'^.*/', '', regex=True)\n .str.replace('.jpg', '', regex=False)\n + '__' + melted['target_name']\n )\n return melted[['sample_id', 'target']]\n\ndef post_process_biomass(df_preds, force_clover_zero=True):\n ordered_cols = [\"Dry_Green_g\", \"Dry_Clover_g\", \"Dry_Dead_g\", \"GDM_g\", \"Dry_Total_g\"]\n for c in ordered_cols:\n if c not in df_preds.columns:\n df_preds[c] = 0.0\n df_out = df_preds.copy()\n\n # フラグが True のときだけ強制ゼロにする\n if force_clover_zero:\n df_out['Dry_Clover_g'] = 0.0\n\n # GDM と Dry_Total を導出\n df_out['GDM_g'] = df_out['Dry_Green_g'] + df_out['Dry_Clover_g']\n df_out['Dry_Total_g'] = df_out['GDM_g'] + df_out['Dry_Dead_g']\n\n df_out['GDM_g'] = df_out['GDM_g'].clip(lower=0.0)\n df_out['Dry_Total_g'] = df_out['Dry_Total_g'].clip(lower=0.0)\n\n return df_out\n\nprint(\"Loading Data...\")\n# Load Train (Metadata Split)\ntrain_df = pd.read_csv(cfg.SPLIT_PATH) \n\n# --- FIX: Remove pre-existing embedding columns to prevent duplication ---\ncols_to_keep = [c for c in train_df.columns if not c.startswith('emb')]\ntrain_df = train_df[cols_to_keep]\n# -----------------------------------------------------------------------\n\n# Ensure train paths match local environment\nif not str(train_df['image_path'].iloc[0]).startswith('/'):\n train_df['image_path'] = train_df['image_path'].apply(lambda p: str(cfg.DATA_PATH / 'train' / os.path.basename(p)))\n\n# Load Test\ntest_df_raw = pd.read_csv(cfg.DATA_PATH / 'test.csv')\ntest_df = pivot_table(test_df_raw)\ntest_df['image_path'] = test_df['image_path'].apply(lambda p: str(cfg.DATA_PATH / p))\n\n# =========================================================================================\n# 3. FEATURE EXTRACTION: SIGLIP IMAGE EMBEDDINGS\n# =========================================================================================\ndef split_image(image, patch_size=520, overlap=16):\n h, w, c = image.shape\n stride = patch_size - overlap\n patches = []\n for y in range(0, h, stride):\n for x in range(0, w, stride):\n y2 = min(y + patch_size, h)\n x2 = min(x + patch_size, w)\n y1 = max(0, y2 - patch_size) # Ensure fixed size\n x1 = max(0, x2 - patch_size)\n patch = image[y1:y2, x1:x2, :]\n patches.append(patch)\n return patches\n\ndef compute_embeddings(model_path, df):\n print(f\"Computing Embeddings for {len(df)} images...\")\n model = AutoModel.from_pretrained(model_path, local_files_only=True).eval().to(cfg.DEVICE)\n processor = AutoImageProcessor.from_pretrained(model_path)\n \n EMBEDDINGS = []\n \n for _, row in tqdm(df.iterrows(), total=len(df)):\n try:\n img = cv2.imread(row['image_path'])\n if img is None: raise ValueError(\"Image not found\")\n img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n patches = split_image(img, patch_size=cfg.PATCH_SIZE, overlap=cfg.OVERLAP)\n images = [Image.fromarray(p) for p in patches]\n \n # Batch process patches\n inputs = processor(images=images, return_tensors=\"pt\").to(cfg.DEVICE)\n with torch.no_grad():\n features = model.get_image_features(**inputs)\n \n # Average pooling of patches\n avg_embed = features.mean(dim=0).cpu().numpy()\n EMBEDDINGS.append(avg_embed)\n except Exception as e:\n print(f\"Error processing {row['image_path']}: {e}\")\n # Fallback zero embedding\n EMBEDDINGS.append(np.zeros(1152))\n \n torch.cuda.empty_cache()\n return np.stack(EMBEDDINGS)\n\n# Compute Features\ntrain_embeddings = compute_embeddings(cfg.SIGLIP_PATH, train_df)\ntest_embeddings = compute_embeddings(cfg.SIGLIP_PATH, test_df)\n\n# Create Feature DataFrames\nemb_cols = [f\"emb{i}\" for i in range(train_embeddings.shape[1])]\ntrain_feat_df = pd.concat([train_df, pd.DataFrame(train_embeddings, columns=emb_cols)], axis=1)\ntest_feat_df = pd.concat([test_df, pd.DataFrame(test_embeddings, columns=emb_cols)], axis=1)\n\n# Double check column counts\nprint(f\"Train Features Shape: {train_feat_df.shape}\")\nprint(f\"Test Features Shape: {test_feat_df.shape}\")\n\n# =========================================================================================\n# 4. FEATURE EXTRACTION: SEMANTIC FEATURES (TEXT PROBING)\n# =========================================================================================\ndef generate_semantic_features(image_embeddings_np, model_path):\n print(\"Generating Semantic Features...\")\n model = AutoModel.from_pretrained(model_path).to(cfg.DEVICE)\n tokenizer = AutoTokenizer.from_pretrained(model_path)\n \n # Anchors\n concept_groups = {\n \"bare\": [\"bare soil\", \"dirt ground\", \"sparse vegetation\", \"exposed earth\"],\n \"sparse\": [\"low density pasture\", \"thin grass\", \"short clipped grass\"],\n \"medium\": [\"average pasture cover\", \"medium height grass\", \"grazed pasture\"],\n \"dense\": [\"dense tall pasture\", \"thick grassy volume\", \"high biomass\", \"overgrown vegetation\"],\n \"green\": [\"lush green vibrant pasture\", \"photosynthesizing leaves\", \"fresh growth\"],\n \"dead\": [\"dry brown dead grass\", \"yellow straw\", \"senesced material\", \"standing hay\"],\n \"clover\": [\"white clover\", \"trifolium repens\", \"broadleaf legume\", \"clover flowers\"],\n \"grass\": [\"ryegrass\", \"blade-like leaves\", \"fescue\", \"grassy sward\"]\n }\n \n # Encode Concepts\n concept_vectors = {}\n with torch.no_grad():\n for name, prompts in concept_groups.items():\n inputs = tokenizer(prompts, padding=\"max_length\", return_tensors=\"pt\").to(cfg.DEVICE)\n emb = model.get_text_features(**inputs)\n emb = emb / emb.norm(p=2, dim=-1, keepdim=True)\n concept_vectors[name] = emb.mean(dim=0, keepdim=True)\n \n # Compute Scores\n img_tensor = torch.tensor(image_embeddings_np, dtype=torch.float32).to(cfg.DEVICE)\n img_tensor = img_tensor / img_tensor.norm(p=2, dim=-1, keepdim=True)\n \n scores = {}\n for name, vec in concept_vectors.items():\n scores[name] = torch.matmul(img_tensor, vec.T).cpu().numpy().flatten()\n \n df_scores = pd.DataFrame(scores)\n # Ratios\n df_scores['ratio_greenness'] = df_scores['green'] / (df_scores['green'] + df_scores['dead'] + 1e-6)\n df_scores['ratio_clover'] = df_scores['clover'] / (df_scores['clover'] + df_scores['grass'] + 1e-6)\n df_scores['ratio_cover'] = (df_scores['dense'] + df_scores['medium']) / (df_scores['bare'] + df_scores['sparse'] + 1e-6)\n \n torch.cuda.empty_cache()\n return df_scores.values\n\n# Combine for semantic generation to ensure consistency\nall_emb = np.vstack([train_embeddings, test_embeddings])\nall_semantic = generate_semantic_features(all_emb, cfg.SIGLIP_PATH)\n\nsem_train = all_semantic[:len(train_df)]\nsem_test = all_semantic[len(train_df):]\n\n# =========================================================================================\n# 5. SUPERVISED EMBEDDING ENGINE\n# =========================================================================================\nclass SupervisedEmbeddingEngine:\n def __init__(self, n_pca=0.80, n_pls=8, n_gmm=6, random_state=42):\n self.scaler = StandardScaler()\n self.pca = PCA(n_components=n_pca, random_state=random_state)\n self.pls = PLSRegression(n_components=n_pls, scale=False)\n self.gmm = GaussianMixture(n_components=n_gmm, covariance_type='diag', random_state=random_state)\n self.pls_fitted_ = False\n\n def fit(self, X, y=None, X_semantic=None):\n # Scale\n X_scaled = self.scaler.fit_transform(X)\n \n # Unsupervised\n self.pca.fit(X_scaled)\n self.gmm.fit(X_scaled)\n \n # Supervised\n if y is not None:\n self.pls.fit(X_scaled, y)\n self.pls_fitted_ = True\n return self\n\n def transform(self, X, X_semantic=None):\n X_scaled = self.scaler.transform(X)\n \n features = [self.pca.transform(X_scaled)]\n \n if self.pls_fitted_:\n features.append(self.pls.transform(X_scaled))\n \n features.append(self.gmm.predict_proba(X_scaled))\n \n if X_semantic is not None:\n # Normalize semantic\n sem_norm = (X_semantic - np.mean(X_semantic, axis=0)) / (np.std(X_semantic, axis=0) + 1e-6)\n features.append(sem_norm)\n \n return np.hstack(features)\n\n# =========================================================================================\n# 6. TRAINING & INFERENCE (5-FOLD CV)\n# =========================================================================================\ndef weighted_r2(y_true, y_pred, weights):\n \"\"\"\n y_true, y_pred: shape (n_samples, n_targets) in original scale\n weights: array-like length n_targets\n \"\"\"\n w = np.array(weights)\n W = np.tile(w, (y_true.shape[0], 1))\n y_true_f = y_true.flatten()\n y_pred_f = y_pred.flatten()\n W_f = W.flatten()\n mu = np.sum(W_f * y_true_f) / np.sum(W_f)\n ss_res = np.sum(W_f * (y_true_f - y_pred_f) ** 2)\n ss_tot = np.sum(W_f * (y_true_f - mu) ** 2)\n return 1.0 - ss_res / (ss_tot + 1e-12)\n\ndef cross_validate_predict_oof(model_cls, model_params, train_data, test_data, sem_tr, sem_te, feature_engine):\n \"\"\"\n OOF 対応版:\n - 戻り値: test_preds_mean (n_test x n_targets), oof_preds (n_train x n_targets), cv_info dict\n \"\"\"\n target_max_arr = np.array([cfg.TARGET_MAX[t] for t in cfg.TARGET_NAMES], dtype=float)\n n_targets = len(cfg.TARGET_NAMES)\n n_train = len(train_data)\n n_test = len(test_data)\n\n oof_preds = np.zeros((n_train, n_targets), dtype=float)\n test_preds_accum = np.zeros((n_test, n_targets), dtype=float)\n fold_scores = []\n\n n_splits = int(train_data['fold'].nunique())\n\n # Pre-extract raw arrays\n X_train_full = train_data[emb_cols].values.astype(np.float32)\n X_test_raw = test_data[emb_cols].values.astype(np.float32)\n y_train_full = train_data[cfg.TARGET_NAMES].values.astype(np.float32)\n\n for fold in range(n_splits):\n print(f\"Processing Fold {fold}...\")\n train_mask = train_data['fold'] != fold\n valid_mask = ~train_mask\n\n X_tr = X_train_full[train_mask]\n X_val = X_train_full[valid_mask]\n\n y_tr = y_train_full[train_mask] / target_max_arr # 学習時は正規化\n # y_val_true は元スケールで評価するため保存\n y_val_true = y_train_full[valid_mask].copy()\n\n sem_tr_fold = sem_tr[train_mask]\n sem_val_fold = sem_tr[valid_mask]\n\n # Feature Engine: fit on train fold\n engine = deepcopy(feature_engine)\n engine.fit(X_tr, y=y_tr, X_semantic=sem_tr_fold)\n\n x_tr_eng = engine.transform(X_tr, X_semantic=sem_tr_fold)\n x_val_eng = engine.transform(X_val, X_semantic=sem_val_fold)\n x_te_eng = engine.transform(X_test_raw, X_semantic=sem_te)\n\n # containers for this fold\n fold_val_pred = np.zeros((len(x_val_eng), n_targets), dtype=float)\n fold_test_pred = np.zeros((n_test, n_targets), dtype=float)\n\n\n for k in range(n_targets):\n target_name = cfg.TARGET_NAMES[k]\n\n # Dry_Clover の扱いを設定フラグで制御する\n if target_name == 'Dry_Clover_g' and cfg.FORCE_CLOVER_ZERO:\n # 固定する場合（従来の挙動）\n fold_val_pred[:, k] = 0.0\n fold_test_pred[:, k] = 0.0\n else:\n # モデルで学習・予測する場合\n mp = model_params.copy()\n esr = mp.pop('early_stopping_rounds', None)\n model = model_cls(**mp)\n\n # y_val_scaled must match training scale (y_tr)\n y_val_scaled = y_train_full[valid_mask] / target_max_arr\n\n if isinstance(model, CatBoostRegressor):\n if esr is not None:\n model.fit(\n x_tr_eng,\n y_tr[:, k],\n eval_set=(x_val_eng, y_val_scaled[:, k]),\n early_stopping_rounds=esr,\n verbose=False\n )\n else:\n model.fit(x_tr_eng, y_tr[:, k])\n elif isinstance(model, LGBMRegressor):\n if esr is not None:\n model.fit(\n x_tr_eng,\n y_tr[:, k],\n eval_set=[(x_val_eng, y_val_scaled[:, k])],\n eval_metric='l2',\n callbacks=[lgb.early_stopping(stopping_rounds=esr)]\n )\n else:\n model.fit(x_tr_eng, y_tr[:, k])\n else:\n # sklearn models (HistGradientBoosting etc.)\n model.fit(x_tr_eng, y_tr[:, k])\n\n\n\n pred_val = model.predict(x_val_eng)\n pred_test = model.predict(x_te_eng)\n\n fold_val_pred[:, k] = pred_val * target_max_arr[k]\n fold_test_pred[:, k] = pred_test * target_max_arr[k]\n \n\n # OOF に格納（元データのインデックス順に合わせる）\n oof_preds[valid_mask, :] = fold_val_pred\n\n # テスト予測を累積\n test_preds_accum += fold_test_pred\n\n # fold の加重R2 を計算（元スケール）\n fold_score = weighted_r2(y_val_true, fold_val_pred, cfg.R2_WEIGHTS)\n fold_scores.append(fold_score)\n print(f\"Fold {fold} weighted R2: {fold_score:.6f}\")\n\n # fold 平均でのテスト予測\n test_preds_mean = test_preds_accum / n_splits\n\n # CV summary\n cv_mean = float(np.mean(fold_scores))\n cv_std = float(np.std(fold_scores))\n print(f\"CV weighted R2 mean: {cv_mean:.6f} std: {cv_std:.6f}\")\n\n # 保存（後でアンサンブル最適化に使えるように）\n pd.DataFrame(oof_preds, columns=cfg.TARGET_NAMES).to_csv(\"oof_preds.csv\", index=False)\n pd.DataFrame(test_preds_mean, columns=cfg.TARGET_NAMES).to_csv(\"test_preds_mean.csv\", index=False)\n\n return test_preds_mean, oof_preds, {'fold_scores': fold_scores, 'mean': cv_mean, 'std': cv_std}\n\n\n# Model Parameters (Optimized)\nparams_cat = {\n # 'iterations': 1900, 'learning_rate': 0.045, 'depth': 4, 'l2_leaf_reg': 0.56, \n 'iterations': 4000, 'learning_rate': 0.01, 'depth': 4, 'l2_leaf_reg': 2.0,\n # 'random_strength': 0.045, 'bagging_temperature': 0.98, 'verbose': 0, 'random_state': 42,\n 'random_strength': 0.045, 'bagging_temperature': 1.2, 'verbose': 0, 'random_state': 42,\n 'allow_writing_files': False,\n 'early_stopping_rounds': 150\n}\nparams_xgb = { # Using GradientBoostingRegressor as proxy\n 'n_estimators': 1354, 'learning_rate': 0.010, 'max_depth': 3, 'subsample': 0.60, \n 'random_state': 42\n}\nparams_lgbm = {\n 'n_estimators': 807, 'learning_rate': 0.014, 'num_leaves': 48, 'min_child_samples': 19, \n # 'n_estimators': 1600, 'learning_rate': 0.01, 'num_leaves': 80, 'min_child_samples': 25, \n 'subsample': 0.745, 'colsample_bytree': 0.745, 'reg_alpha': 0.21, 'reg_lambda': 3.78, # 'reg_lambda': 3.78,\n 'verbose': -1, 'random_state': 42,\n 'early_stopping_rounds': 200\n}\nparams_hist = {\n 'max_iter': 300, 'learning_rate': 0.05, 'max_depth': None, 'l2_regularization': 0.44,\n 'random_state': 42,\n 'n_iter_no_change': 20, # sklearn の早期停止パラメータ \n 'validation_fraction': 0.1\n}\n\n# feat_engine = SupervisedEmbeddingEngine(n_pca=0.80, n_pls=8, n_gmm=6)\nfeat_engine = SupervisedEmbeddingEngine(n_pca=0.99, n_pls=14, n_gmm=10)\n\nprint(\"Training & Inferring Models...\")\n\n# 1. HistGradientBoosting\nprint(\"Model: HistGradientBoosting\")\npred_hist_mean, oof_hist, info_hist = cross_validate_predict_oof(\n HistGradientBoostingRegressor, params_hist,\n train_feat_df, test_feat_df, sem_train, sem_test, feat_engine\n)\nprint(f\"HistGB CV weighted R2: mean={info_hist['mean']:.6f}, std={info_hist['std']:.6f}\")\npd.DataFrame(oof_hist, columns=cfg.TARGET_NAMES).to_csv(\"oof_hist.csv\", index=False)\npd.DataFrame(pred_hist_mean, columns=cfg.TARGET_NAMES).to_csv(\"test_hist.csv\", index=False)\n\n# 2. GradientBoosting\nprint(\"Model: GradientBoosting\")\npred_gb_mean, oof_gb, info_gb = cross_validate_predict_oof(\n GradientBoostingRegressor, params_xgb,\n train_feat_df, test_feat_df, sem_train, sem_test, feat_engine\n)\nprint(f\"GB CV weighted R2: mean={info_gb['mean']:.6f}, std={info_gb['std']:.6f}\")\npd.DataFrame(oof_gb, columns=cfg.TARGET_NAMES).to_csv(\"oof_gb.csv\", index=False)\npd.DataFrame(pred_gb_mean, columns=cfg.TARGET_NAMES).to_csv(\"test_gb.csv\", index=False)\n\n# 3. CatBoost\nprint(\"Model: CatBoost\")\npred_cat_mean, oof_cat, info_cat = cross_validate_predict_oof(\n CatBoostRegressor, params_cat,\n train_feat_df, test_feat_df, sem_train, sem_test, feat_engine\n)\nprint(f\"CatBoost CV weighted R2: mean={info_cat['mean']:.6f}, std={info_cat['std']:.6f}\")\npd.DataFrame(oof_cat, columns=cfg.TARGET_NAMES).to_csv(\"oof_cat.csv\", index=False)\npd.DataFrame(pred_cat_mean, columns=cfg.TARGET_NAMES).to_csv(\"test_cat.csv\", index=False)\n\n# 4. LightGBM\nprint(\"Model: LightGBM\")\npred_lgbm_mean, oof_lgbm, info_lgbm = cross_validate_predict_oof(\n LGBMRegressor, params_lgbm,\n train_feat_df, test_feat_df, sem_train, sem_test, feat_engine\n)\nprint(f\"LGBM CV weighted R2: mean={info_lgbm['mean']:.6f}, std={info_lgbm['std']:.6f}\")\npd.DataFrame(oof_lgbm, columns=cfg.TARGET_NAMES).to_csv(\"oof_lgb.csv\", index=False)\npd.DataFrame(pred_lgbm_mean, columns=cfg.TARGET_NAMES).to_csv(\"test_lgb.csv\", index=False)\n\n\n\n# =========================================================================================\n# 7. ENSEMBLING & SUBMISSION\n# =========================================================================================\nprint(\"Ensembling and Post-processing...\")\n# # Simple Average Ensemble 簡易グリッド中コメントアウト\n# final_pred = (pred_hist_mean + pred_gb_mean + pred_cat_mean + pred_lgbm_mean) / 4.0\n# --- OOF-based weight optimization (replace simple average) ---ここから：重み最適化（簡易グリッド） ---\nimport numpy as np\n\npreds_list = [pred_hist_mean, pred_gb_mean, pred_cat_mean, pred_lgbm_mean]\nmodel_names = ['hist','gb','cat','lgb']\n\n# Try to load per-model OOF files named oof_hist.csv, oof_gb.csv, oof_cat.csv, oof_lgb.csv\nper_model_oofs = []\nper_ok = True\nfor mn in model_names:\n fname = f'oof_{mn}.csv'\n if os.path.exists(fname):\n per_model_oofs.append(pd.read_csv(fname)[cfg.TARGET_NAMES].values)\n else:\n per_ok = False\n break\n\nif per_ok:\n # coarse random simplex grid\n rng = np.random.RandomState(42)\n grid = []\n for _ in range(500):\n v = rng.rand(len(preds_list))\n v = v / v.sum()\n grid.append(v)\n grid.append(np.ones(len(preds_list))/len(preds_list))\n\n # load true train targets (same order as OOF files)\n try:\n y_train = pd.read_csv('train_targets.csv')[cfg.TARGET_NAMES].values\n except Exception:\n # fallback to train_feat_df if it contains targets\n if set(cfg.TARGET_NAMES).issubset(set(train_feat_df.columns)):\n y_train = train_feat_df[cfg.TARGET_NAMES].values\n else:\n raise FileNotFoundError(\"train_targets.csv not found and train_feat_df lacks target columns.\")\n\n def weighted_r2_local(y_true, y_pred, weights):\n w = np.array(weights)\n W = np.tile(w, (y_true.shape[0], 1))\n y_true_f = y_true.flatten()\n y_pred_f = y_pred.flatten()\n W_f = W.flatten()\n mu = np.sum(W_f * y_true_f) / np.sum(W_f)\n ss_res = np.sum(W_f * (y_true_f - y_pred_f) ** 2)\n ss_tot = np.sum(W_f * (y_true_f - mu) ** 2)\n return 1.0 - ss_res / (ss_tot + 1e-12)\n\n best = {'score': -1e9, 'weights': np.ones(len(preds_list))/len(preds_list)}\n for w in grid:\n pred_oof = sum(w[i] * per_model_oofs[i] for i in range(len(per_model_oofs)))\n score = weighted_r2_local(y_train, pred_oof, cfg.R2_WEIGHTS)\n if score > best['score']:\n best = {'score': score, 'weights': w}\n best_weights = best['weights']\n print(\"Selected weights (OOF):\", dict(zip(model_names, np.round(best_weights,3))), \"OOF score:\", best['score'])\nelse:\n # fallback: equal weights\n best_weights = np.ones(len(preds_list)) / len(preds_list)\n print(\"Per-model OOF files not found. Using equal weights:\", best_weights)\n\n# apply weights to test preds\nw = best_weights / best_weights.sum()\nfinal_pred = sum(w[i] * preds_list[i] for i in range(len(preds_list)))\n\n# --- 必須: final_pred を DataFrame に代入する（重み最適化直後に置く） ---\ntest_feat_df[cfg.TARGET_NAMES] = final_pred\n\n# sanity check（任意だが推奨）\nprint(\"final_pred shape:\", final_pred.shape)\nfor i, t in enumerate(cfg.TARGET_NAMES):\n col = final_pred[:, i]\n print(f\"{t}: min={col.min():.4f}, mean={col.mean():.4f}, max={col.max():.4f}\")\n\n# save chosen weights for record\nwith open('ensemble_weights.txt', 'w') as f:\n f.write(str(dict(zip(model_names, np.round(w,3)))))\n# --- ここまで：重み最適化（簡易） ---\n\n\n# Post-process (Mass Balance) — 学習時と同じフラグを使う\ntest_processed = post_process_biomass(test_feat_df, force_clover_zero=cfg.FORCE_CLOVER_ZERO)\n\n# Create Submission File\nsub_df = melt_table(test_processed)\noutput_path = \"submission_siglip.csv\"\nsub_df.to_csv(output_path, index=False)\n\nprint(f\"✓ Siglip submission generated: {output_path}\")\nprint(sub_df.head())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T17:57:33.828127Z","iopub.execute_input":"2026-01-27T17:57:33.828401Z","iopub.status.idle":"2026-01-27T18:18:43.611199Z","shell.execute_reply.started":"2026-01-27T17:57:33.828374Z","shell.execute_reply":"2026-01-27T18:18:43.610374Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%writefile csiro_infer.py\nfrom PIL import Image\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import KFold, GroupKFold, StratifiedGroupKFold\nfrom tqdm.auto import tqdm\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\nfrom torch.optim import AdamW\nfrom transformers import get_cosine_schedule_with_warmup\n\nfrom torch.utils.data import Dataset, DataLoader\nfrom torchvision import transforms as T\n\nimport os\nfrom pathlib import Path\nimport timm\nimport warnings \n\nwarnings.filterwarnings('ignore')\ntqdm.pandas()\n\nclass RegressionDataset(Dataset):\n def __init__(self, data, transform=None):\n self.data = data\n self.transform = transform\n def __len__(self):\n return self.data.shape[0]\n\n def __getitem__(self, idx):\n item = self.data.iloc[idx]\n image = item.image\n targets = [item['Dry_Green_g'], item['Dry_Clover_g'], item['Dry_Dead_g']]\n width, height = image.size\n mid_point = width // 2\n left_image = image.crop((0, 0, mid_point, height))\n right_image = image.crop((mid_point, 0, width, height))\n\n if self.transform is not None:\n left_image = self.transform(left_image)\n right_image = self.transform(right_image)\n\n return left_image, right_image, targets\n\ndef get_test_dataloaders(data, image_size, batch_size):\n res = []\n for trans in [None, T.RandomHorizontalFlip(p=1.0), T.RandomVerticalFlip(p=1.0)]:\n transform = T.Compose([\n T.Resize(image_size),\n T.ToTensor(),\n T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])\n ])\n if trans:\n transform = T.Compose([\n T.Resize(image_size),\n trans,\n T.ToTensor(),\n T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])\n ])\n dataset = RegressionDataset(data, transform=transform)\n res.append(DataLoader(dataset, batch_size=batch_size, shuffle=False, num_workers=4))\n return res\n\n\nclass FiLM(nn.Module):\n def __init__(self, feat_dim):\n super().__init__()\n self.mlp = nn.Sequential(\n nn.Linear(feat_dim, feat_dim // 2), \n nn.ReLU(inplace=True), \n nn.Linear(feat_dim // 2, feat_dim * 2)\n )\n\n def forward(self, context):\n gamma_beta = self.mlp(context)\n return torch.chunk(gamma_beta, 2, dim=1)\n\nclass CSIROModelRegressor(nn.Module):\n def __init__(self, model_name, pretrained=True, num_classes=3, dropout=0.0, freeze_backbone=False):\n super().__init__()\n self.backbone = timm.create_model(model_name, pretrained=pretrained, num_classes=0, global_pool='avg')\n\n self.film = FiLM(self.backbone.num_features)\n\n self.dropout = nn.Dropout(dropout)\n\n def make_head():\n return nn.Sequential(\n nn.Linear(self.backbone.num_features * 2, 8),\n nn.ReLU(inplace=True),\n nn.Dropout(dropout),\n nn.Linear(8, 1),\n )\n\n self.head_green = make_head()\n self.head_clover = make_head()\n self.head_dead = make_head()\n\n self.softplus = nn.Softplus(beta=1.0)\n\n if freeze_backbone:\n for p in self.backbone.parameters():\n p.requires_grad = False\n\n\n def forward(self, left_img, right_img):\n left_feat = self.backbone(left_img)\n right_feat = self.backbone(right_img)\n\n context = (left_feat + right_feat) / 2\n gamma, beta = self.film(context)\n\n left_feat_modulated = left_feat * (1 + gamma) + beta\n right_feat_modulated = right_feat * (1 + gamma) + beta\n\n combined = torch.cat([left_feat_modulated, right_feat_modulated], dim=1)\n\n green = self.softplus(self.head_green(combined)) \n clover = self.softplus(self.head_clover(combined))\n dead = self.softplus(self.head_dead(combined)) \n\n logits = torch.cat([green, clover, dead], dim=1)\n\n return logits\n\ndef predict(model, dataloader, device):\n model.to(device)\n model.eval()\n\n all_outputs = []\n with torch.no_grad():\n for left_images, right_images, targets in dataloader:\n left_images = left_images.to(device)\n right_images = right_images.to(device)\n\n outputs = model(left_images, right_images)\n all_outputs.append(outputs.detach().cpu())\n\n outputs = torch.cat(all_outputs).numpy()\n return outputs\n\ndef predict_loaders(model, dataloaders, device):\n all_outputs = []\n for dataloader in dataloaders:\n outputs = predict(model, dataloader, device)\n all_outputs.append(outputs)\n avg_outputs = np.mean(all_outputs, axis=0)\n return avg_outputs\n\ndef predict_folds(dataloaders,models_dir):\n device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')\n\n all_preds = []\n for model_file in Path(models_dir).glob('*.pth'):\n model = CSIROModelRegressor(CFG.MODEL_NAME, pretrained=False, num_classes=3)\n model.load_state_dict(torch.load(model_file))\n preds = predict_loaders(model, dataloaders, device)\n all_preds.append(preds)\n\n avg_preds = np.mean(all_preds, axis=0)\n return avg_preds\n\n\nclass CFG:\n DATA_PATH=\"/kaggle/input/csiro-biomass/\"\n TEST_DATA_PATH=\"/kaggle/input/csiro-biomass/test.csv\"\n MODEL_NAME=\"vit_large_patch16_dinov3_qkvb\"\n MODELS_DIR ='/kaggle/input/modelv3/pytorch/default/1/models_retrained'\n IMG_SIZE=(512,512)\n\n\ntest_df = pd.read_csv(CFG.TEST_DATA_PATH)\n\ntest_df['target'] = 0.0\ntest_df[['sample_id_prefix', 'sample_id_suffix']] = test_df.sample_id.str.split('__', expand=True)\n\ntest_data_df = test_df.groupby(['sample_id_prefix', 'image_path']).apply(lambda df: df.set_index('target_name').target)\ntest_data_df.reset_index(inplace=True)\ntest_data_df.columns.name = None\n\ntest_data_df['image'] = test_data_df.image_path.progress_apply(lambda path: Image.open(CFG.DATA_PATH + path).convert('RGB'))\n\ntest_loaders = get_test_dataloaders(test_data_df, CFG.IMG_SIZE, 32)\npreds = predict_folds(test_loaders,models_dir=CFG.MODELS_DIR)\n\ntest_data_df[['Dry_Green_g', 'Dry_Clover_g', 'Dry_Dead_g']] = preds\ntest_data_df['Dry_Green_g'] = test_data_df['Dry_Green_g'].apply(lambda x: 0.0 if x < 0.09 else x)\ntest_data_df['Dry_Clover_g'] = test_data_df['Dry_Clover_g'].apply(lambda x: 0.0 if x < 0.09 else x)\ntest_data_df['Dry_Dead_g'] = test_data_df['Dry_Dead_g'].apply(lambda x: 0.0 if x < 0.09 else x)\ntest_data_df['Dry_Total_g'] = test_data_df.GDM_g + test_data_df.Dry_Dead_g\n\nTARGETS = ['Dry_Green_g', 'Dry_Dead_g', 'Dry_Clover_g', 'GDM_g', 'Dry_Total_g']\n\nsubmission_rows = []\nfor idx, row in test_data_df.iterrows():\n image_id = row['image_path'].split('/')[-1].replace('.jpg', '')\n \n for target_name in TARGETS:\n sample_id = f\"{image_id}__{target_name}\"\n prediction = row[target_name]\n \n # Post-processing：Dry_Clover_gが0になりやすくしている箇所\n if target_name == \"Dry_Clover_g\":\n prediction = prediction * 0.9 # 0.8\n elif target_name == \"Dry_Dead_g\":\n if prediction > 20:\n prediction *= 1.1\n elif prediction < 10:\n prediction *= 0.9\n \n submission_rows.append({\n 'sample_id': sample_id,\n 'target': prediction\n })\n\nsub_df = pd.DataFrame(submission_rows)\nsub_df.to_csv('submission_dinov2026.csv', index=False)\n\nprint(sub_df)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:18:43.613064Z","iopub.execute_input":"2026-01-27T18:18:43.613397Z","iopub.status.idle":"2026-01-27T18:18:43.622755Z","shell.execute_reply.started":"2026-01-27T18:18:43.613372Z","shell.execute_reply":"2026-01-27T18:18:43.622059Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python csiro_infer.py","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:18:43.623645Z","iopub.execute_input":"2026-01-27T18:18:43.623878Z","iopub.status.idle":"2026-01-27T18:20:07.54281Z","shell.execute_reply.started":"2026-01-27T18:18:43.623859Z","shell.execute_reply":"2026-01-27T18:20:07.542036Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport os\n\n# =============================================================================\n# CONFIGURATION\n# =============================================================================\n# Weights for the ensemble (Must sum to 1.0)\n# Adjust based on which model had better local CV or Public LB score.\n# Example: If Siglip was better, give it 0.6.\nW_SIGLIP = 0.45 # 0.35\nW_DINO = 0.55 # 0.65\n\nFILES = {\n 'siglip': 'submission_siglip.csv',\n 'dino': 'submission_dinov2026.csv'\n}\n\nOUTPUT_FILE = 'submission72.csv'\n\n# Target definitions required for Mass Balance\nALL_TARGETS = ['Dry_Green_g', 'Dry_Clover_g', 'Dry_Dead_g', 'GDM_g', 'Dry_Total_g']\n\n# =============================================================================\n# HELPER FUNCTIONS\n# =============================================================================\n\ndef enforce_mass_balance(df_wide, fixed_clover=None):\n \"\"\"\n Applies Orthogonal Projection to enforce biological constraints:\n 1. Dry_Green_g + Dry_Clover_g = GDM_g\n 2. GDM_g + Dry_Dead_g = Dry_Total_g\n \n If fixed_clover is True, Dry_Clover_g is kept fixed and only other targets are adjusted.\n \n This finds the closest set of values to the predictions that satisfy \n the constraints (minimizing Euclidean distance modification).\n \"\"\"\n # 1. Ensure columns are in the specific order for the matrix math\n # Vector x = [Green, Clover, Dead, GDM, Total]\n ordered_cols = ['Dry_Green_g', 'Dry_Clover_g', 'Dry_Dead_g', 'GDM_g', 'Dry_Total_g']\n \n # Extract values: Shape (5, N_samples)\n Y = df_wide[ordered_cols].values.T\n \n if fixed_clover:\n # Keep Dry_Clover_g fixed, adjust only other targets\n # We have: Green + Clover_fixed = GDM, so GDM = Green + Clover_fixed\n # And: GDM + Dead = Total, so Total = GDM + Dead = Green + Clover_fixed + Dead\n # Extract fixed Clover values\n clover_fixed = Y[1, :].copy() # Dry_Clover_g is index 1\n # Adjust: GDM = Green + Clover_fixed\n Y[3, :] = Y[0, :] + clover_fixed # GDM_g\n # Adjust: Total = GDM + Dead = Green + Clover_fixed + Dead\n Y[4, :] = Y[3, :] + Y[2, :] # Dry_Total_g\n # Keep Green and Dead as is (or apply minimal adjustment if needed)\n # Clover stays fixed (already set)\n Y_reconciled = Y\n else:\n # Original method: adjust all targets\n # 2. Define Constraint Matrix C where Cx = 0\n # Eq 1: 1*Gr + 1*Cl + 0*De - 1*GDM + 0*Tot = 0\n # Eq 2: 0*Gr + 0*Cl + 1*De + 1*GDM - 1*Tot = 0\n C = np.array([\n [1, 1, 0, -1, 0],\n [0, 0, 1, 1, -1]\n ])\n \n # 3. Calculate Projection Matrix P = I - C^T * (C * C^T)^-1 * C\n C_T = C.T\n try:\n inv_CCt = np.linalg.inv(C @ C_T)\n P = np.eye(5) - C_T @ inv_CCt @ C\n except np.linalg.LinAlgError:\n # Fallback if singular (unlikely with this specific matrix)\n print(\"Warning: Singular matrix in projection. Skipping constraint enforcement.\")\n return df_wide\n\n # 4. Apply Projection\n Y_reconciled = P @ Y\n \n # 5. Transpose back to (N_samples, 5) and clip negatives\n Y_reconciled = Y_reconciled.T\n Y_reconciled = np.maximum(0, Y_reconciled) \n \n # 6. Update DataFrame\n df_out = df_wide.copy()\n df_out[ordered_cols] = Y_reconciled\n \n return df_out\n\ndef robust_ensemble(file_paths, weights):\n print(f\"--- Starting Ensemble ---\")\n print(f\"Weights: {weights}\")\n print(\"NOTE: Using DINO-only for Dry_Clover_g (better detection)\")\n \n dfs = []\n for name, path in file_paths.items():\n if not os.path.exists(path):\n raise FileNotFoundError(f\"Missing file: {path}\")\n \n # Read and sort by sample_id to ensure alignment\n df = pd.read_csv(path).sort_values('sample_id').reset_index(drop=True)\n dfs.append(df)\n print(f\"Loaded {name}: {len(df)} rows\")\n\n # 1. Check alignment\n base_ids = dfs[0]['sample_id']\n if not all(df['sample_id'].equals(base_ids) for df in dfs[1:]):\n raise ValueError(\"Sample IDs do not match between submission files!\")\n\n # 2. Split by target_name to handle Dry_Clover_g separately\n # Split sample_id into image_id and target_name\n dfs_split = []\n for df in dfs:\n df_split = df.copy()\n df_split[['image_id', 'target_name']] = df_split['sample_id'].str.rsplit('__', n=1, expand=True)\n dfs_split.append(df_split)\n \n # Get DINO and SigLIP dataframes (identify by order in file_paths)\n dino_idx = list(file_paths.keys()).index('dino')\n siglip_idx = list(file_paths.keys()).index('siglip')\n dino_df = dfs_split[dino_idx]\n siglip_df = dfs_split[siglip_idx]\n \n # 3. Separate targets: Dry_Clover_g uses DINO only, others use ensemble\n ensemble_results = []\n \n for target in ALL_TARGETS:\n # Filter for this target\n dino_target = dino_df[dino_df['target_name'] == target].copy()\n siglip_target = siglip_df[siglip_df['target_name'] == target].copy()\n \n if target == 'Dry_Clover_g':\n # Use DINO only for Clover\n print(f\"Using DINO-only for {target}\")\n ensemble_results.append(dino_target[['sample_id', 'target']])\n else:\n # Ensemble for other targets\n # Merge on sample_id to align\n merged = pd.merge(\n dino_target[['sample_id', 'target']].rename(columns={'target': 'dino_pred'}),\n siglip_target[['sample_id', 'target']].rename(columns={'target': 'siglip_pred'}),\n on='sample_id'\n )\n \n # Weighted average\n w_vec = np.array([weights['dino'], weights['siglip']])\n w_vec = w_vec / w_vec.sum()\n \n merged['target'] = merged['dino_pred'] * w_vec[0] + merged['siglip_pred'] * w_vec[1]\n ensemble_results.append(merged[['sample_id', 'target']])\n \n # 4. Combine all targets\n ensemble_df = pd.concat(ensemble_results, ignore_index=True)\n print(\"Weighted average complete (DINO-only for Clover).\")\n\n # 5. Prepare for Mass Balance (Convert Long -> Wide)\n ensemble_df[['image_id', 'target_name']] = ensemble_df['sample_id'].str.rsplit('__', n=1, expand=True)\n \n # Pivot\n wide_df = ensemble_df.pivot(index='image_id', columns='target_name', values='target').reset_index()\n\n # 6. Apply Robust Constraints (with Dry_Clover_g fixed)\n print(\"Applying Mass Balance Constraints (Dry_Clover_g fixed to DINO values)...\")\n wide_balanced = enforce_mass_balance(wide_df, fixed_clover=True)\n\n # 7. Convert back (Wide -> Long)\n long_balanced = wide_balanced.melt(\n id_vars='image_id', \n value_vars=ALL_TARGETS,\n var_name='target_name',\n value_name='target'\n )\n\n # Reconstruct sample_id\n long_balanced['sample_id'] = long_balanced['image_id'] + '__' + long_balanced['target_name']\n\n # 8. Final Formatting\n final_submission = long_balanced[['sample_id', 'target']].sort_values('sample_id').reset_index(drop=True)\n\n return final_submission\n\n# =============================================================================\n# EXECUTION\n# =============================================================================\nif __name__ == \"__main__\":\n \n # Define weights\n ensemble_weights = {\n 'siglip': W_SIGLIP,\n 'dino': W_DINO\n }\n \n try:\n # Run Ensemble\n submission = robust_ensemble(FILES, ensemble_weights)\n \n # Save\n submission.to_csv(OUTPUT_FILE, index=False)\n print(f\"\\nSuccess! Saved to {OUTPUT_FILE}\")\n print(submission.head())\n \n # Sanity Check Stats\n print(\"\\nStats:\")\n print(submission['target'].describe())\n \n except Exception as e:\n print(f\"\\nError during ensembling: {e}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:07.544264Z","iopub.execute_input":"2026-01-27T18:20:07.544589Z","iopub.status.idle":"2026-01-27T18:20:07.610783Z","shell.execute_reply.started":"2026-01-27T18:20:07.544538Z","shell.execute_reply":"2026-01-27T18:20:07.610118Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# now import timm fresh\nimport timm, sys\nprint(\"python:\", sys.version)\nprint(\"timm:\", timm.__version__)\nprint(\"timm file:\", timm.__file__)\nprint(\"dinov3 matches:\", timm.list_models(\"*dinov3*\")[:50])\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:07.612913Z","iopub.execute_input":"2026-01-27T18:20:07.6137Z","iopub.status.idle":"2026-01-27T18:20:08.985057Z","shell.execute_reply.started":"2026-01-27T18:20:07.613662Z","shell.execute_reply":"2026-01-27T18:20:08.98427Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n# Config\nimport os, gc, math, cv2, numpy as np, pandas as pd\nfrom tqdm import tqdm\nimport torch, torch.nn as nn, torch.optim as optim\nfrom torch.optim.lr_scheduler import LambdaLR\nfrom torch.utils.data import Dataset, DataLoader\nimport albumentations as A\nfrom albumentations.pytorch import ToTensorV2\nimport time\nfrom timm.utils import ModelEmaV2\nfrom sklearn.model_selection import KFold, StratifiedGroupKFold\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\ntorch.backends.cuda.matmul.allow_tf32 = True\ntorch.backends.cudnn.allow_tf32 = True\ntorch.backends.cudnn.benchmark = True\ntorch.set_float32_matmul_precision(\"high\")\n\nclass CFG:\n CREATE_SUBMISSION = True\n USE_TQDM = False\n PRETRAINED_DIR = None\n PRETRAINED = True\n BASE_PATH = '/kaggle/input/csiro-biomass'\n SEED = 82947501\n FOLDS_TO_TRAIN = [0,1,2,3,4]\n TRAIN_CSV = os.path.join(BASE_PATH, 'train.csv')\n TRAIN_IMAGE_DIR = os.path.join(BASE_PATH, 'train')\n TEST_IMAGE_DIR = '/kaggle/input/csiro-biomass/test'\n TEST_CSV = '/kaggle/input/csiro-biomass/test.csv'\n SUBMISSION_DIR = './'\n MODEL_DIR = '/kaggle/input/baseline-dinov3/pytorch/default/1/baseline-dinov3'\n # MODEL_DIR = './models'\n N_FOLDS = 5\n\n MODEL_NAME = 'vit_huge_plus_patch16_dinov3.lvd1689m'\n BACKBONE_PATH = '/kaggle/input/vit-huge-plus-patch16-dinov3-lvd1689m/vit_huge_plus_patch16_dinov3.lvd1689m_backbone.pth'\n DINO_GRAD_CHECKPOINTING = False\n\n IMG_SIZE = 512\n\n VAL_TTA_TIMES = 1\n TTA_STEPS = 1\n \n \n BATCH_SIZE = 1\n GRAD_ACC = 8 # 4\n NUM_WORKERS = 4\n EPOCHS = 30\n FREEZE_EPOCHS = 1 # 0\n WARMUP_EPOCHS = 3\n LR_REST = 1e-3\n LR_BACKBONE = 1e-4 # 5e-4\n WD = 1e-2\n EMA_DECAY = 0.999 # 0.9\n CLIP_GRAD_NORM = 1.0\n PATIENCE = 5\n TARGET_COLS = ['Dry_Total_g', 'GDM_g', 'Dry_Green_g']\n DERIVED_COLS = ['Dry_Clover_g', 'Dry_Dead_g']\n ALL_TARGET_COLS = ['Dry_Green_g','Dry_Dead_g','Dry_Clover_g','GDM_g','Dry_Total_g']\n R2_WEIGHTS = np.array([0.1, 0.1, 0.1, 0.2, 0.5])\n LOSS_WEIGHTS = np.array([0.1, 0.1, 0.1, 0.0, 0.0])\n DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n\nos.makedirs(CFG.MODEL_DIR, exist_ok=True)\nprint(f'Device : {CFG.DEVICE}')\nprint(f'Backbone: {CFG.MODEL_NAME} | Input: {CFG.IMG_SIZE}')\nprint(f'Freeze Epochs: {CFG.FREEZE_EPOCHS} | Warmup: {CFG.WARMUP_EPOCHS}')\nprint(f'EMA Decay: {CFG.EMA_DECAY} | Grad Acc: {CFG.GRAD_ACC}')","metadata":{"papermill":{"duration":37.523526,"end_time":"2026-01-05T05:09:15.453763","exception":false,"start_time":"2026-01-05T05:08:37.930237","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:08.986099Z","iopub.execute_input":"2026-01-27T18:20:08.986343Z","iopub.status.idle":"2026-01-27T18:20:42.357315Z","shell.execute_reply.started":"2026-01-27T18:20:08.986321Z","shell.execute_reply":"2026-01-27T18:20:42.356603Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Metrics\ndef weighted_r2_score(y_true: np.ndarray, y_pred: np.ndarray):\n weights = CFG.R2_WEIGHTS\n r2_scores = []\n for i in range(y_true.shape[1]):\n yt = y_true[:, i]; yp = y_pred[:, i]\n ss_res = np.sum((yt - yp) ** 2)\n ss_tot = np.sum((yt - np.mean(yt)) ** 2)\n r2 = 1 - ss_res / ss_tot if ss_tot > 0 else 0.0\n r2_scores.append(r2)\n r2_scores = np.array(r2_scores)\n weighted = np.sum(r2_scores * weights) / np.sum(weights)\n return weighted, r2_scores\n\ndef weighted_r2_score_global(y_true: np.ndarray, y_pred: np.ndarray):\n weights = CFG.R2_WEIGHTS\n flat_true = y_true.reshape(-1)\n flat_pred = y_pred.reshape(-1)\n w = np.tile(weights, y_true.shape[0])\n mean_w = np.sum(w * flat_true) / np.sum(w)\n ss_res = np.sum(w * (flat_true - flat_pred) ** 2)\n ss_tot = np.sum(w * (flat_true - mean_w) ** 2)\n global_r2 = 1 - ss_res / ss_tot if ss_tot > 0 else 0.0\n avg_r2, per_r2 = weighted_r2_score(y_true, y_pred)\n return global_r2, avg_r2, per_r2\n\ndef analyze_errors(val_df, y_true, y_pred, targets, top_n=5):\n print(f'\\n--- Top {top_n} High Loss Samples per Target ---')\n y_true = np.array(y_true)\n y_pred = np.array(y_pred)\n \n for i, target in enumerate(targets):\n errors = np.abs(y_true[:, i] - y_pred[:, i])\n top_indices = np.argsort(errors)[::-1][:top_n]\n \n print(f'\\nTarget: {target}')\n print(f'{\"Index\":<6} | {\"Image Path\":<40} | {\"True\":<10} | {\"Pred\":<10} | {\"AbsErr\":<10}')\n print('-' * 90)\n \n for idx in top_indices:\n path = val_df.iloc[idx]['image_path']\n path_disp = os.path.basename(path)\n t_val = y_true[idx, i]\n p_val = y_pred[idx, i]\n err = errors[idx]\n print(f'{idx:<6} | {path_disp:<40} | {t_val:<10.4f} | {p_val:<10.4f} | {err:<10.4f}')\ndef analyze_errors(val_df, y_true, y_pred, targets, top_n=5):\n print(f'\\n--- Top {top_n} High Loss Samples per Target ---')\n y_true = np.array(y_true)\n y_pred = np.array(y_pred)\n \n for i, target in enumerate(targets):\n errors = np.abs(y_true[:, i] - y_pred[:, i])\n top_indices = np.argsort(errors)[::-1][:top_n]\n \n print(f'\\nTarget: {target}')\n header = f'{\"Index\":<6} | {\"Image Path\":<40} | {\"State\":<6} | {\"True\":<10} | {\"Pred\":<10} | {\"AbsErr\":<10}'\n print(header)\n print('-' * len(header))\n \n for idx in top_indices:\n path = val_df.iloc[idx]['image_path']\n path_disp = os.path.basename(path)\n state = val_df.iloc[idx]['State'] if 'State' in val_df.columns else 'NA'\n t_val = y_true[idx, i]\n p_val = y_pred[idx, i]\n err = errors[idx]\n print(f'{idx:<6} | {path_disp:<40} | {str(state):<6} | {t_val:<10.4f} | {p_val:<10.4f} | {err:<10.4f}')\ndef compare_train_val(tr_df, val_df, targets, show_plots=True):\n \"\"\"Quick comparison of target distributions and metadata between train and val splits.\"\"\"\n print(\"\\n--- Train / Val Comparison ---\")\n\n for t in targets:\n tr = tr_df.get(t, pd.Series(dtype=float)).dropna()\n val = val_df.get(t, pd.Series(dtype=float)).dropna()\n print(f\"\\nTarget: {t}\")\n print(f\" Train: n={len(tr)} mean={tr.mean():.3f} std={tr.std():.3f} min={tr.min():.3f} max={tr.max():.3f}\")\n print(f\" Val : n={len(val)} mean={val.mean():.3f} std={val.std():.3f} min={val.min():.3f} max={val.max():.3f}\")\n if show_plots:\n try:\n plt.figure(figsize=(6, 3))\n sns.kdeplot(tr, label='train', fill=True)\n sns.kdeplot(val, label='val', fill=True)\n plt.legend()\n plt.title(f'Distribution: {t}')\n plt.show()\n except Exception as e:\n print(' Could not plot distributions for', t, '-', e)\n\n # Compare Sampling_Date and State if present\n if 'Sampling_Date' in tr_df.columns:\n try:\n tr_dates = pd.to_datetime(tr_df['Sampling_Date'], errors='coerce')\n val_dates = pd.to_datetime(val_df['Sampling_Date'], errors='coerce')\n print(\"\\nSampling_Date range:\")\n print(f\" Train: {tr_dates.min()} -> {tr_dates.max()} (missing {tr_dates.isna().sum()})\")\n print(f\" Val : {val_dates.min()} -> {val_dates.max()} (missing {val_dates.isna().sum()})\")\n except Exception as e:\n print(' Could not parse Sampling_Date:', e)\n if 'State' in tr_df.columns:\n print(\"\\nState distribution (train vs val):\")\n tr_state = tr_df['State'].value_counts(normalize=True)\n val_state = val_df['State'].value_counts(normalize=True)\n state_df = pd.concat([tr_state, val_state], axis=1, keys=['train', 'val']).fillna(0)\n\n print(state_df)\n\n \ndef biomass_loss(outputs, labels, w=None):\n total, gdm, green, clover, dead = outputs\n mse = nn.MSELoss()\n huber = nn.SmoothL1Loss(beta=5.0) # Huber loss for robust regression (beta=5.0 as recommended)\n \n l_green = huber(green.squeeze(), labels[:,0])\n l_dead = huber(dead.squeeze(), labels[:,1]) # Use Huber loss for Dead\n l_clover = huber(clover.squeeze(), labels[:,2])\n l_gdm = huber(gdm.squeeze(), labels[:,3])\n l_total = huber(total.squeeze(), labels[:,4])\n\n # Stack per-target losses in the SAME order as CFG.ALL_TARGET_COLS\n losses = torch.stack([l_green, l_dead, l_clover, l_gdm, l_total])\n # losses = torch.stack([l_green, l_dead, l_clover])\n\n # Use provided weights, or default to CFG.R2_WEIGHTS\n if w is None:\n return losses.mean()\n w = torch.as_tensor(w, device=losses.device, dtype=losses.dtype)\n w = w / w.sum()\n return (losses * w).sum()","metadata":{"papermill":{"duration":0.025723,"end_time":"2026-01-05T05:09:15.502256","exception":false,"start_time":"2026-01-05T05:09:15.476533","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:42.35848Z","iopub.execute_input":"2026-01-27T18:20:42.359227Z","iopub.status.idle":"2026-01-27T18:20:42.378004Z","shell.execute_reply.started":"2026-01-27T18:20:42.359205Z","shell.execute_reply":"2026-01-27T18:20:42.377305Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Transforms\ndef get_train_transforms():\n return A.Compose([\n A.Resize(CFG.IMG_SIZE, CFG.IMG_SIZE),\n A.HorizontalFlip(p=0.5),\n A.VerticalFlip(p=0.5),\n A.RandomRotate90(p=0.5),\n A.Rotate(limit=(-10, 10), p=0.3, interpolation=cv2.INTER_LINEAR, border_mode=cv2.BORDER_REFLECT_101),\n A.ColorJitter(brightness=0.1, contrast=0.1, saturation=0.1, hue=0.05, p=0.5),\n A.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),\n ToTensorV2()\n ], p=1.0)\n\ndef get_val_transforms():\n return A.Compose([\n A.Resize(CFG.IMG_SIZE, CFG.IMG_SIZE),\n A.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),\n ToTensorV2()\n ], p=1.0)\n\ndef get_tta_transforms(mode=0):\n # mode 0: original\n # mode 1: hflip\n # mode 2: vflip\n # mode 3: rotate90\n transforms_list = [\n A.Resize(CFG.IMG_SIZE, CFG.IMG_SIZE),\n ]\n \n if mode == 1:\n transforms_list.append(A.HorizontalFlip(p=1.0))\n elif mode == 2:\n transforms_list.append(A.VerticalFlip(p=1.0))\n elif mode == 3:\n transforms_list.append(A.RandomRotate90(p=1.0)) # RandomRotate90 with p=1.0 rotates 90, 180, 270 randomly? \n # Albumentations RandomRotate90 rotates by 90, 180, 270. \n # Reference uses transforms.RandomRotation([90, 90]) which is exactly 90 degrees.\n # To match exactly 90 degrees in Albumentations, we might need Rotate(limit=(90,90), p=1.0)\n # But RandomRotate90 is standard TTA. Let's use Rotate(limit=(90,90)) to be precise if that's what reference does.\n # Reference: transforms.RandomRotation([90, 90]) -> rotates by exactly 90 degrees.\n transforms_list.append(A.Rotate(limit=(90, 90), p=1.0, interpolation=cv2.INTER_LINEAR, border_mode=cv2.BORDER_REFLECT_101))\n\n transforms_list.extend([\n A.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),\n ToTensorV2()\n ])\n \n return A.Compose(transforms_list, p=1.0)\ndef clean_image(img):\n # 1. Safe Crop (Remove artifacts at the bottom)\n h, w = img.shape[:2]\n # Cut bottom 10% where artifacts often appear\n img = img[0:int(h*0.90), :] \n\n # 2. Inpaint Date Stamp (Remove orange text)\n hsv = cv2.cvtColor(img, cv2.COLOR_RGB2HSV)\n # Define orange color range (adjust as needed)\n lower = np.array([5, 150, 150])\n upper = np.array([25, 255, 255])\n mask = cv2.inRange(hsv, lower, upper)\n\n # Dilate mask to cover text edges and reduce noise\n mask = cv2.dilate(mask, np.ones((3,3), np.uint8), iterations=2)\n\n # Inpaint if mask is not empty\n if np.sum(mask) > 0:\n img = cv2.inpaint(img, mask, 3, cv2.INPAINT_TELEA)\n\n return img\nclass BiomassDataset(Dataset):\n def __init__(self, df, transform, img_dir):\n self.df = df\n self.transform = transform\n self.img_dir = img_dir\n self.paths = df['image_path'].values\n self.labels = df[CFG.ALL_TARGET_COLS].values.astype(np.float32)\n\n def __len__(self):\n return len(self.df)\n\n def __getitem__(self, idx):\n path = os.path.join(self.img_dir, os.path.basename(self.paths[idx]))\n img = cv2.imread(path)\n if img is None:\n img = np.zeros((1000, 2000, 3), dtype=np.uint8)\n img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n img = clean_image(img)\n h, w, _ = img.shape\n mid = w // 2\n left = img[:, :mid]\n right = img[:, mid:]\n left = self.transform(image=left)['image']\n right = self.transform(image=right)['image']\n label = torch.from_numpy(self.labels[idx])\n return left, right, label","metadata":{"papermill":{"duration":0.021348,"end_time":"2026-01-05T05:09:15.546114","exception":false,"start_time":"2026-01-05T05:09:15.524766","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:42.379154Z","iopub.execute_input":"2026-01-27T18:20:42.379424Z","iopub.status.idle":"2026-01-27T18:20:42.40932Z","shell.execute_reply.started":"2026-01-27T18:20:42.379404Z","shell.execute_reply":"2026-01-27T18:20:42.40859Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Layers\nclass LocalMambaBlock(nn.Module):\n \"\"\"\n Lightweight Mamba-style block (Gated CNN) from the reference notebook.\n Efficiently mixes tokens with linear complexity.\n \"\"\"\n def __init__(self, dim, kernel_size=5, dropout=0.0):\n super().__init__()\n self.norm = nn.LayerNorm(dim)\n # Depthwise conv mixes spatial information locally\n self.dwconv = nn.Conv1d(dim, dim, kernel_size=kernel_size, padding=kernel_size // 2, groups=dim)\n self.gate = nn.Linear(dim, dim)\n self.proj = nn.Linear(dim, dim)\n self.drop = nn.Dropout(dropout)\n\n def forward(self, x):\n # x: (Batch, Tokens, Dim)\n shortcut = x\n x = self.norm(x)\n # Gating mechanism\n g = torch.sigmoid(self.gate(x))\n x = x * g\n # Spatial mixing via 1D Conv (requires transpose)\n x = x.transpose(1, 2) # -> (B, D, N)\n x = self.dwconv(x)\n x = x.transpose(1, 2) # -> (B, N, D)\n # Projection\n x = self.proj(x)\n x = self.drop(x)\n return shortcut + x\n","metadata":{"papermill":{"duration":0.026162,"end_time":"2026-01-05T05:09:15.59418","exception":false,"start_time":"2026-01-05T05:09:15.568018","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:42.410165Z","iopub.execute_input":"2026-01-27T18:20:42.41041Z","iopub.status.idle":"2026-01-27T18:20:42.435183Z","shell.execute_reply.started":"2026-01-27T18:20:42.410384Z","shell.execute_reply":"2026-01-27T18:20:42.434379Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Model\nclass BiomassModel(nn.Module):\n def __init__(self, model_name, pretrained=True, backbone_path=None):\n super().__init__()\n self.model_name = model_name\n self.backbone_path = backbone_path\n \n # 1. Load Backbone with global_pool='' to keep patch tokens\n # (B, 197, 1024) instead of (B, 1024)\n self.backbone = timm.create_model(self.model_name, pretrained=False, num_classes=0, global_pool='')\n \n # 2. Enable Gradient Checkpointing (Crucial for ViT-Large memory!)\n if hasattr(self.backbone, 'set_grad_checkpointing') and CFG.DINO_GRAD_CHECKPOINTING:\n self.backbone.set_grad_checkpointing(True)\n print(\"✓ Gradient Checkpointing enabled (saves ~50% VRAM)\")\n \n nf = self.backbone.num_features\n \n # 3. Mamba Fusion Neck\n # Mixes the concatenated tokens [Left, Right]\n self.fusion = nn.Sequential(\n LocalMambaBlock(nf, kernel_size=5, dropout=0.1),\n LocalMambaBlock(nf, kernel_size=5, dropout=0.1)\n )\n \n # 4. Pooling & Heads\n self.pool = nn.AdaptiveAvgPool1d(1)\n \n # Heads (using the same logic as before, but on fused features)\n self.head_green_raw = nn.Sequential(\n nn.Linear(nf, nf//2), nn.GELU(), nn.Dropout(0.2), \n nn.Linear(nf//2, 1), nn.Softplus()\n )\n self.head_clover_raw = nn.Sequential(\n nn.Linear(nf, nf//2), nn.GELU(), nn.Dropout(0.2), \n nn.Linear(nf//2, 1), nn.Softplus()\n )\n self.head_dead_raw = nn.Sequential(\n nn.Linear(nf, nf//2), nn.GELU(), nn.Dropout(0.2), \n nn.Linear(nf//2, 1), nn.Softplus()\n )\n \n if pretrained:\n self.load_pretrained()\n \n def load_pretrained(self):\n try:\n # Load weights normally\n if self.backbone_path and os.path.exists(self.backbone_path):\n print(f\"Loading backbone weights from local file: {self.backbone_path}\")\n sd = torch.load(self.backbone_path, map_location='cpu')\n # Handle common checkpoint wrappers (e.g. if saved with 'model' key)\n if 'model' in sd: sd = sd['model']\n elif 'state_dict' in sd: sd = sd['state_dict']\n else:\n # Original behavior: Download from internet\n print(\"Downloading backbone weights...\")\n sd = timm.create_model(self.model_name, pretrained=True, num_classes=0, global_pool='').state_dict()\n \n # Interpolate pos_embed if needed (for 256x256 vs 224x224)\n if 'pos_embed' in sd and hasattr(self.backbone, 'pos_embed'):\n pe_ck = sd['pos_embed']\n pe_m = self.backbone.pos_embed\n if pe_ck.shape != pe_m.shape:\n print(f\"Interpolating pos_embed: {pe_ck.shape} -> {pe_m.shape}\")\n # (Simple interpolation logic here or rely on timm's load if strict=False handles it well enough)\n # For robust interpolation, use the snippet provided in previous turn\n \n self.backbone.load_state_dict(sd, strict=False)\n print('Pretrained weights loaded.')\n except Exception as e:\n print(f'Warning: pretrained load failed: {e}')\n \n def forward(self, left, right):\n # 1. Extract Tokens (B, N, D)\n # Note: ViT usually returns [CLS, Patch1, Patch2...]\n # We remove CLS token for spatial mixing, or keep it. Let's keep it.\n x_l = self.backbone(left)\n x_r = self.backbone(right)\n \n # 2. Concatenate Left and Right tokens along sequence dimension\n # (B, N, D) + (B, N, D) -> (B, 2N, D)\n x_cat = torch.cat([x_l, x_r], dim=1)\n \n # 3. Apply Mamba Fusion\n # This allows tokens from Left image to interact with tokens from Right image\n x_fused = self.fusion(x_cat)\n \n # 4. Global Pooling\n # (B, 2N, D) -> (B, D, 2N) -> (B, D, 1) -> (B, D)\n x_pool = self.pool(x_fused.transpose(1, 2)).flatten(1)\n \n # 5. Prediction Heads\n green = self.head_green_raw(x_pool)\n clover = self.head_clover_raw(x_pool)\n dead = self.head_dead_raw(x_pool)\n \n # Summation logic\n gdm = green + clover\n total = gdm + dead\n \n return total, gdm, green, clover, dead\n \n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:42.436079Z","iopub.execute_input":"2026-01-27T18:20:42.436312Z","iopub.status.idle":"2026-01-27T18:20:42.455515Z","shell.execute_reply.started":"2026-01-27T18:20:42.436293Z","shell.execute_reply":"2026-01-27T18:20:42.455002Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Utility Functions\ndef set_backbone_requires_grad(model: BiomassModel, requires_grad: bool):\n for p in model.backbone.parameters():\n p.requires_grad = requires_grad\n\n\ndef build_optimizer(model: BiomassModel):\n # 1. Get backbone parameter IDs for exclusion\n backbone_ids = {id(p) for p in model.backbone.parameters()}\n \n # 2. Separate params into backbone vs. everything else (heads, fusion, etc.)\n backbone_params = []\n rest_params = []\n \n for p in model.parameters():\n if p.requires_grad:\n if id(p) in backbone_ids:\n backbone_params.append(p)\n else:\n rest_params.append(p)\n \n return optim.AdamW([\n {'params': backbone_params, 'lr': CFG.LR_BACKBONE, 'weight_decay': CFG.WD},\n {'params': rest_params, 'lr': CFG.LR_REST, 'weight_decay': CFG.WD},\n])\n\ndef build_scheduler(optimizer):\n def lr_lambda(epoch):\n e = max(0, epoch - 1)\n if e < CFG.WARMUP_EPOCHS:\n return float(e + 1) / float(max(1, CFG.WARMUP_EPOCHS))\n progress = (e - CFG.WARMUP_EPOCHS) / float(max(1, CFG.EPOCHS - CFG.WARMUP_EPOCHS))\n return 0.5 * (1.0 + math.cos(math.pi * progress))\n return LambdaLR(optimizer, lr_lambda)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:42.456245Z","iopub.execute_input":"2026-01-27T18:20:42.456422Z","iopub.status.idle":"2026-01-27T18:20:42.476474Z","shell.execute_reply.started":"2026-01-27T18:20:42.456405Z","shell.execute_reply":"2026-01-27T18:20:42.475957Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Training and Validation Loops \n\nfrom contextlib import nullcontext\n\nUSE_BF16 = True\nAMP_DTYPE = torch.bfloat16 if USE_BF16 else torch.float16\n\nscaler = torch.amp.GradScaler(\n 'cuda',\n enabled=(torch.cuda.is_available() and AMP_DTYPE == torch.float16)\n)\n\ndef autocast_ctx():\n if not torch.cuda.is_available():\n return nullcontext()\n return torch.amp.autocast(device_type='cuda', dtype=AMP_DTYPE)\n\ndef _as_col(x: torch.Tensor, bs: int) -> torch.Tensor:\n \"\"\"Force predictions to (B,1) regardless of model head returning (B,) or (B,1).\"\"\"\n if x.ndim == 1:\n return x.view(bs, 1)\n if x.ndim == 2:\n return x\n return x.view(bs, 1)\n\ndef _ensure_2d_lab(lab: torch.Tensor, bs: int) -> torch.Tensor:\n \"\"\"Force labels to (B,T).\"\"\"\n if lab.ndim == 1:\n return lab.view(bs, -1)\n return lab\n\ndef _pred_pack(p_total, p_gdm, p_green, p_clover, p_dead, bs: int) -> torch.Tensor:\n \"\"\"\n Pack predictions in the exact order expected by your metric:\n CFG.ALL_TARGET_COLS = ['Dry_Green_g','Dry_Dead_g','Dry_Clover_g','GDM_g','Dry_Total_g']\n \"\"\"\n pg = _as_col(p_green, bs)\n pd = _as_col(p_dead, bs)\n pc = _as_col(p_clover, bs)\n pgdm = _as_col(p_gdm, bs)\n pt = _as_col(p_total, bs)\n return torch.cat([pg, pd, pc, pgdm, pt], dim=1) # (B,5)\n\n@torch.inference_mode()\ndef valid_epoch(eval_model, loader, device):\n eval_model.eval()\n\n n = len(loader.dataset)\n n_targets = len(CFG.ALL_TARGET_COLS)\n\n preds_cpu = torch.empty((n, n_targets), dtype=torch.float32)\n labels_cpu = torch.empty((n, n_targets), dtype=torch.float32)\n\n total_loss = 0.0\n offset = 0\n\n for l, r, lab in loader:\n bs = l.size(0)\n l = l.to(device, non_blocking=True)\n r = r.to(device, non_blocking=True)\n lab = lab.to(device, non_blocking=True)\n\n with autocast_ctx():\n p_total, p_gdm, p_green, p_clover, p_dead = eval_model(l, r)\n loss = biomass_loss((p_total, p_gdm, p_green, p_clover, p_dead),\n lab, w=CFG.LOSS_WEIGHTS)\n\n total_loss += loss.detach().float().item() * bs\n\n batch_pred = _pred_pack(p_total, p_gdm, p_green, p_clover, p_dead, bs).float().cpu()\n batch_lab = _ensure_2d_lab(lab, bs).float().cpu()\n\n # Safety: ensure dims match (avoids silent 4/5 bugs)\n if batch_pred.shape[1] != n_targets or batch_lab.shape[1] != n_targets:\n raise RuntimeError(\n f\"Target dim mismatch: pred={batch_pred.shape}, lab={batch_lab.shape}, \"\n f\"CFG.ALL_TARGET_COLS={n_targets}\"\n )\n\n preds_cpu[offset:offset+bs] = batch_pred\n labels_cpu[offset:offset+bs] = batch_lab\n offset += bs\n\n pred_all = preds_cpu.numpy()\n true_labels = labels_cpu.numpy()\n global_r2, avg_r2, per_r2 = weighted_r2_score_global(true_labels, pred_all)\n\n return total_loss / n, global_r2, avg_r2, per_r2, pred_all, true_labels\n\n\n@torch.inference_mode()\ndef valid_epoch_tta(eval_model, loaders, device):\n \"\"\"\n Fixed: always accumulate (N,5). Works even if a head outputs (B,1).\n Assumes each loader iterates in identical order (shuffle=False).\n \"\"\"\n eval_model.eval()\n assert len(loaders) > 0\n\n n = len(loaders[0].dataset)\n n_targets = len(CFG.ALL_TARGET_COLS)\n\n labels_cpu = torch.empty((n, n_targets), dtype=torch.float32)\n preds_sum = torch.zeros((n, n_targets), dtype=torch.float32)\n\n total_loss = 0.0\n\n for tta_i, loader in enumerate(loaders):\n offset = 0\n tta_loss = 0.0\n\n for l, r, lab in loader:\n bs = l.size(0)\n l = l.to(device, non_blocking=True)\n r = r.to(device, non_blocking=True)\n lab = lab.to(device, non_blocking=True)\n\n with autocast_ctx():\n p_total, p_gdm, p_green, p_clover, p_dead = eval_model(l, r)\n loss = biomass_loss((p_total, p_gdm, p_green, p_clover, p_dead),\n lab, w=CFG.LOSS_WEIGHTS)\n\n tta_loss += loss.detach().float().item() * bs\n\n batch_pred = _pred_pack(p_total, p_gdm, p_green, p_clover, p_dead, bs).float().cpu()\n preds_sum[offset:offset+bs] += batch_pred\n\n if tta_i == 0:\n batch_lab = _ensure_2d_lab(lab, bs).float().cpu()\n if batch_lab.shape[1] != n_targets:\n raise RuntimeError(f\"Label dim mismatch: {batch_lab.shape} vs {n_targets}\")\n labels_cpu[offset:offset+bs] = batch_lab\n\n offset += bs\n\n total_loss += tta_loss / n\n\n avg_preds = (preds_sum / len(loaders)).numpy()\n true_labels = labels_cpu.numpy()\n global_r2, avg_r2, per_r2 = weighted_r2_score_global(true_labels, avg_preds)\n\n return total_loss / len(loaders), global_r2, avg_r2, per_r2, avg_preds, true_labels\n\n\ndef train_epoch(model, loader, opt, scheduler, device, ema: ModelEmaV2 | None = None):\n model.train()\n running = 0.0\n\n opt.zero_grad(set_to_none=True)\n itera = tqdm(loader, desc='train', leave=False) if CFG.USE_TQDM else loader\n\n for i, (l, r, lab) in enumerate(itera):\n bs = l.size(0)\n l = l.to(device, non_blocking=True)\n r = r.to(device, non_blocking=True)\n lab = lab.to(device, non_blocking=True)\n\n with autocast_ctx():\n p_total, p_gdm, p_green, p_clover, p_dead = model(l, r)\n loss = biomass_loss((p_total, p_gdm, p_green, p_clover, p_dead),\n lab, w=CFG.LOSS_WEIGHTS)\n loss = loss / CFG.GRAD_ACC\n\n\n if not torch.isfinite(loss):\n print(\"Non-finite loss detected; skipping batch\")\n opt.zero_grad(set_to_none=True)\n continue\n\n if scaler.is_enabled():\n scaler.scale(loss).backward()\n else:\n loss.backward()\n\n running += loss.detach().float().item() * bs * CFG.GRAD_ACC\n\n do_step = ((i + 1) % CFG.GRAD_ACC == 0) or ((i + 1) == len(loader))\n if do_step:\n if scaler.is_enabled():\n scaler.unscale_(opt)\n torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)\n scaler.step(opt)\n scaler.update()\n else:\n torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)\n opt.step()\n\n if ema is not None:\n ema.update(model.module if hasattr(model, \"module\") else model)\n\n opt.zero_grad(set_to_none=True)\n\n scheduler.step()\n return running / len(loader.dataset)\n","metadata":{"papermill":{"duration":0.048482,"end_time":"2026-01-05T05:09:15.664902","exception":false,"start_time":"2026-01-05T05:09:15.61642","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:42.477376Z","iopub.execute_input":"2026-01-27T18:20:42.477657Z","iopub.status.idle":"2026-01-27T18:20:42.501875Z","shell.execute_reply.started":"2026-01-27T18:20:42.477629Z","shell.execute_reply":"2026-01-27T18:20:42.501275Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # === MAIN TRAINING LOOP === #学習コメントアウトのセル\n\n# # Helper for accurate GPU timings\n# def _sync():\n# if torch.cuda.is_available():\n# torch.cuda.synchronize()\n\n# print('Loading data...')\n# df_long = pd.read_csv(CFG.TRAIN_CSV)\n\n# df_wide = (\n# df_long.pivot(index='image_path', columns='target_name', values='target')\n# .reset_index()\n# )\n# assert df_wide['image_path'].is_unique, 'Leakage risk: duplicate image_path rows'\n\n# # Merge metadata (Sampling_Date, State) for stratification\n# if 'Sampling_Date' in df_long.columns and 'State' in df_long.columns:\n# print('Merging metadata for stratification...')\n# meta_df = df_long[['image_path', 'Sampling_Date', 'State']].drop_duplicates()\n# df_wide = df_wide.merge(meta_df, on='image_path', how='left')\n\n# # Keep necessary columns\n# df_wide = df_wide[['image_path', 'Sampling_Date', 'State'] + CFG.ALL_TARGET_COLS]\n# print(f'{len(df_wide)} training images')\n\n# # Use StratifiedGroupKFold\n# sgkf = StratifiedGroupKFold(n_splits=CFG.N_FOLDS, shuffle=True, random_state=CFG.SEED)\n# oof_true, oof_pred, fold_summary = [], [], []\n\n# # Split based on groups (Sampling_Date) and stratification target (State)\n# groups = df_wide['Sampling_Date']\n# y_stratify = df_wide['State']\n\n# # One place for loader kwargs (fast)\n# DL_KW = dict(\n# num_workers=CFG.NUM_WORKERS,\n# pin_memory=True,\n# persistent_workers=(CFG.NUM_WORKERS > 0),\n# prefetch_factor=4 if CFG.NUM_WORKERS > 0 else None,\n# )\n\n# for fold, (tr_idx, val_idx) in enumerate(sgkf.split(df_wide, y_stratify, groups=groups)):\n# if fold not in CFG.FOLDS_TO_TRAIN:\n# print(f'Skipping fold {fold} as per configuration.')\n# continue\n\n# print('\\n' + '='*70)\n# print(f'FOLD {fold+1}/{CFG.N_FOLDS} | {len(tr_idx)} train / {len(val_idx)} val')\n# print('='*70)\n\n# # NOTE: avoid empty_cache/gc inside epoch loop; only between folds if you really want\n# _sync()\n# torch.cuda.empty_cache()\n# gc.collect()\n\n# tr_df = df_wide.iloc[tr_idx].reset_index(drop=True)\n# val_df = df_wide.iloc[val_idx].reset_index(drop=True)\n\n# tr_set = BiomassDataset(tr_df, get_train_transforms(), CFG.TRAIN_IMAGE_DIR)\n\n# # Create TTA loaders (keep TTAs as requested)\n# val_loaders = []\n# for mode in range(CFG.VAL_TTA_TIMES): # 0: orig, 1: hflip, 2: vflip, 3: rot90\n# val_set_tta = BiomassDataset(val_df, get_tta_transforms(mode), CFG.TRAIN_IMAGE_DIR)\n# val_loader_tta = DataLoader(\n# val_set_tta,\n# batch_size=CFG.BATCH_SIZE,\n# shuffle=False,\n# drop_last=False,\n# **{k: v for k, v in DL_KW.items() if v is not None},\n# )\n# val_loaders.append(val_loader_tta)\n\n# tr_loader = DataLoader(\n# tr_set,\n# batch_size=CFG.BATCH_SIZE,\n# shuffle=True,\n# drop_last=True,\n# **{k: v for k, v in DL_KW.items() if v is not None},\n# )\n\n# print('Building model...')\n# backbone_path = getattr(CFG, 'BACKBONE_PATH', None)\n# model = BiomassModel(CFG.MODEL_NAME, pretrained=CFG.PRETRAINED, backbone_path=backbone_path).to(CFG.DEVICE)\n\n# # Load pretrained fold weights if available (for resuming or fine-tuning)\n# if getattr(CFG, 'PRETRAINED_DIR', None) and os.path.isdir(CFG.PRETRAINED_DIR):\n# pretrained_path = os.path.join(CFG.PRETRAINED_DIR, f'best_model_fold{fold}.pth')\n# if os.path.exists(pretrained_path):\n# try:\n# state = torch.load(pretrained_path, map_location='cpu')\n# if isinstance(state, dict) and ('model_state_dict' in state or 'state_dict' in state):\n# key = 'model_state_dict' if 'model_state_dict' in state else 'state_dict'\n# sd = state[key]\n# else:\n# sd = state\n# model.load_state_dict(sd, strict=False)\n# model.to(CFG.DEVICE)\n# print(f' ✓ Loaded pretrained weights for fold {fold} from {pretrained_path}')\n# except Exception as e:\n# print(f' ✗ Failed to load pretrained fold {fold}: {e}')\n# else:\n# print(f' (No pretrained file for fold {fold} at {pretrained_path})')\n# else:\n# print(' (No PRETRAINED_DIR configured or directory missing)')\n\n# # Single GPU: DO NOT wrap in DataParallel\n# # model = nn.DataParallel(model) # <-- removed\n\n# # Freeze/unfreeze backbone\n# set_backbone_requires_grad(model, False)\n\n# optimizer = build_optimizer(model)\n# scheduler = build_scheduler(optimizer)\n\n# # EMA on the real model\n# ema = ModelEmaV2(model, decay=CFG.EMA_DECAY)\n\n# best_global_r2 = -np.inf\n# best_avg_r2 = -np.inf\n# patience = 0\n# best_fold_preds = None\n# best_fold_true = None\n\n# save_path = os.path.join(CFG.MODEL_DIR, f'best_model_fold{fold}.pth')\n\n# for epoch in range(1, CFG.EPOCHS + 1):\n# if epoch == CFG.FREEZE_EPOCHS + 1:\n# patience = 0\n# set_backbone_requires_grad(model, True)\n# print(f'Epoch {epoch}: backbone unfrozen')\n\n# # ---- Train timing ----\n# _sync()\n# t0 = time.perf_counter()\n# tr_loss = train_epoch(model, tr_loader, optimizer, scheduler, CFG.DEVICE, ema)\n# _sync()\n# t1 = time.perf_counter()\n\n# # choose eval model (EMA weights)\n# eval_model = ema.module if ema is not None else model\n\n# # ---- Val timing (TTA) ----\n# _sync()\n# t2 = time.perf_counter()\n# val_loss, global_r2, avg_r2, per_r2, preds_fold, true_fold = valid_epoch_tta(eval_model, val_loaders, CFG.DEVICE)\n# _sync()\n# t3 = time.perf_counter()\n\n# time_tr = t1 - t0\n# time_val = t3 - t2\n# time_ep = t3 - t0\n\n# per_r2_str = ' | '.join([f'{CFG.ALL_TARGET_COLS[i][:5]}: {r2:.3f}' for i, r2 in enumerate(per_r2)])\n# lrs = [pg['lr'] for pg in optimizer.param_groups]\n# lr_str = ' '.join([f'lr{i}={lr:.3e}' for i, lr in enumerate(lrs)])\n\n# print(\n# f'Fold {fold} | Epoch {epoch:02d} | '\n# f'TLoss {tr_loss:.5f} | VLoss {val_loss:.5f} | '\n# f'avgR2 {avg_r2:.4f} | GlobalR² {global_r2:.4f} '\n# f'{\"[BEST]\" if global_r2 > best_global_r2 else \"\"} | '\n# f'{lr_str} | time_tr={time_tr:.1f}s time_val={time_val:.1f}s time_ep={time_ep:.1f}s'\n# )\n# print(f' → {per_r2_str}')\n\n# if global_r2 > best_global_r2:\n# best_global_r2 = global_r2\n# best_avg_r2 = avg_r2\n\n# # Save EMA weights directly (no CPU clone) for speed\n# # NOTE: safest is to save state_dict tensors as-is; this is typically fine on DGX.\n# torch.save(eval_model.state_dict(), save_path)\n# print(f' → SAVED EMA weights to {save_path} (GlobalR²: {best_global_r2:.4f})')\n\n# patience = 0\n# best_fold_preds = preds_fold\n# best_fold_true = true_fold\n# else:\n# patience += 1\n# if patience >= CFG.PATIENCE:\n# print(f' → EARLY STOP (no improvement in {CFG.PATIENCE} epochs)')\n# break\n\n# # keep memory tidy but avoid heavy cache/gc churn\n# del preds_fold, true_fold\n\n# if best_fold_preds is not None:\n# oof_true.append(best_fold_true)\n# oof_pred.append(best_fold_preds)\n# fold_summary.append({'fold': fold, 'global_r2': best_global_r2, 'avg_r2': best_avg_r2})\n\n# # Cleanup for this fold\n# del model, tr_loader, val_loaders, optimizer, scheduler, ema, eval_model\n# _sync()\n# torch.cuda.empty_cache()\n# gc.collect()\n\n# if oof_true:\n# oof_true_arr = np.concatenate(oof_true, axis=0)\n# oof_pred_arr = np.concatenate(oof_pred, axis=0)\n# oof_global_r2, oof_avg_r2, oof_per_r2 = weighted_r2_score_global(oof_true_arr, oof_pred_arr)\n\n# print('\\nTraining complete! Models saved in:', CFG.MODEL_DIR)\n# print('Fold summary:')\n# for fs in fold_summary:\n# print(f\" Fold {fs['fold']}: Global R² = {fs['global_r2']:.4f}, Avg R² = {fs.get('avg_r2', float('nan')):.4f}\")\n# print(f'OOF Global Weighted R²: {oof_global_r2:.4f} | OOF Avg Target R²: {oof_avg_r2:.4f}')\n# print('OOF Per-target:', dict(zip(CFG.ALL_TARGET_COLS, [f\"{r:.4f}\" for r in oof_per_r2])))\n# else:\n# print('No OOF predictions collected.')\n","metadata":{"papermill":{"duration":0.016335,"end_time":"2026-01-05T05:09:15.715963","exception":false,"start_time":"2026-01-05T05:09:15.699628","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:42.502947Z","iopub.execute_input":"2026-01-27T18:20:42.503239Z","iopub.status.idle":"2026-01-27T18:20:42.522172Z","shell.execute_reply.started":"2026-01-27T18:20:42.503221Z","shell.execute_reply":"2026-01-27T18:20:42.521489Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Inference \n\n# 4. DEFINE TTA TRANSFORMS\n# ===============================================================\ndef get_tta_transforms(num_transforms):\n \"\"\"\n Returns a list of TTA transform pipelines.\n Each pipeline represents a different augmentation view.\n \"\"\"\n normalize = A.Normalize(\n mean=[0.485, 0.456, 0.406],\n std=[0.229, 0.224, 0.225]\n )\n to_tensor = ToTensorV2()\n \n all_tta_transforms = [\n # View 1: Original (no flip)\n A.Compose([\n A.Resize(CFG.IMG_SIZE, CFG.IMG_SIZE),\n normalize,\n to_tensor\n ]),\n \n # View 2: Horizontal Flip\n A.Compose([\n A.Resize(CFG.IMG_SIZE, CFG.IMG_SIZE),\n A.HorizontalFlip(p=1.0),\n normalize,\n to_tensor\n ]),\n \n # View 3: Vertical Flip\n A.Compose([\n A.Resize(CFG.IMG_SIZE, CFG.IMG_SIZE),\n A.VerticalFlip(p=1.0),\n normalize,\n to_tensor\n ]),\n \n # View 4: Both Flips\n A.Compose([\n A.Resize(CFG.IMG_SIZE, CFG.IMG_SIZE),\n A.HorizontalFlip(p=1.0),\n A.VerticalFlip(p=1.0),\n normalize,\n to_tensor\n ]),\n ]\n tta_transforms = all_tta_transforms[:num_transforms]\n return tta_transforms\n\nprint(f\"✓ TTA transforms defined ({CFG.TTA_STEPS} views)\")\n\n# ===============================================================\n# 5. CREATE TEST DATASET\n# ===============================================================\ndef clean_image(img):\n # Safe crop (remove bottom artifacts) + inpaint orange date stamp\n h, w = img.shape[:2]\n img = img[0:int(h * 0.90), :]\n hsv = cv2.cvtColor(img, cv2.COLOR_RGB2HSV)\n lower = np.array([5, 150, 150])\n upper = np.array([25, 255, 255])\n mask = cv2.inRange(hsv, lower, upper)\n mask = cv2.dilate(mask, np.ones((3, 3), np.uint8), iterations=2)\n if np.sum(mask) > 0:\n img = cv2.inpaint(img, mask, 3, cv2.INPAINT_TELEA)\n return img\n\nclass BiomassTestDataset(Dataset):\n \"\"\"\n Test dataset for biomass images.\n Splits each 2000×1000 image into left and right 1000×1000 halves.\n \"\"\"\n def __init__(self, img_dir):\n self.img_dir = img_dir\n self.paths = sorted([\n os.path.join(img_dir, f) for f in os.listdir(img_dir)\n if f.lower().endswith(('.jpg', '.jpeg', '.png'))\n ])\n self.filenames = [os.path.basename(p) for p in self.paths]\n \n def __len__(self):\n return len(self.paths)\n \n def __getitem__(self, idx):\n path = self.paths[idx]\n \n # Read image\n img = cv2.imread(path)\n if img is None:\n print(f\"Warning: Could not read {path}, using blank image\")\n img = np.zeros((1000, 2000, 3), dtype=np.uint8)\n \n # Convert BGR to RGB\n img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n img = clean_image(img)\n # Split into left and right halves\n h, w = img.shape[:2]\n mid = w // 2\n left = img[:, :mid].copy()\n right = img[:, mid:].copy()\n \n return left, right, self.filenames[idx]\n\nprint(\"✓ Test dataset class defined\")\n\n# ===============================================================\n# 8. RUN INFERENCE WITH TTA (UPDATED to honor CFG.FOLDS_TO_TRAIN)\n# ===============================================================\n\n@torch.no_grad()\ndef predict_with_tta(model, left_np, right_np, tta_transforms):\n \"\"\"\n Predict using TTA with a SINGLE model.\n \n Args:\n model: Single trained model\n left_np: Left half of image (numpy array)\n right_np: Right half of image (numpy array)\n tta_transforms: List of augmentation transforms\n \n Returns:\n numpy array: [total, gdm, green] predictions (averaged over TTA)\n \"\"\"\n all_tta_preds = []\n \n # Loop over TTA views\n for tfm in tta_transforms:\n # Apply transform to both halves\n left_tensor = tfm(image=left_np)['image'].unsqueeze(0).to(CFG.DEVICE)\n right_tensor = tfm(image=right_np)['image'].unsqueeze(0).to(CFG.DEVICE)\n \n total, gdm, green, clover, dead = model(left_tensor, right_tensor)\n \n # Extract values\n p_total = total.cpu().item()\n p_gdm = gdm.cpu().item()\n p_green = green.cpu().item()\n \n all_tta_preds.append([p_total, p_gdm, p_green])\n \n # Average across TTA views\n final_pred = np.mean(all_tta_preds, axis=0)\n \n return final_pred\n\n\ndef run_inference():\n \"\"\"\n Main inference function.\n Returns: (predictions_array, image_filenames)\n Notes:\n - Now respects `CFG.FOLDS_TO_TRAIN` (if set) and averages only over successfully loaded folds.\n - If no fold weights are found for the requested folds, an error is raised.\n \"\"\"\n print(\"\\n\" + \"=\"*70)\n print(\"STARTING INFERENCE\")\n print(\"=\"*70)\n \n # Create dataset and loader\n dataset = BiomassTestDataset(CFG.TEST_IMAGE_DIR)\n # Note: batch_size=1 is required for the current predict_with_tta implementation\n loader = DataLoader(\n dataset,\n batch_size=1, \n shuffle=False,\n num_workers=CFG.NUM_WORKERS,\n pin_memory=True\n )\n \n tta_transforms = get_tta_transforms(CFG.TTA_STEPS)\n \n # Initialize accumulator for predictions\n # Shape: (num_samples, 3) for Total, GDM, Green\n accumulated_preds = np.zeros((len(dataset), 3), dtype=np.float32)\n\n # Use configured folds, fallback to full range if not set or empty\n folds_to_use = getattr(CFG, 'FOLDS_TO_TRAIN', list(range(CFG.N_FOLDS)))\n if not folds_to_use:\n folds_to_use = list(range(CFG.N_FOLDS))\n\n print(f\"Folds requested for inference: {folds_to_use}\")\n\n # Use filenames from dataset (guaranteed consistent ordering with loader because shuffle=False)\n filenames = dataset.filenames.copy()\n\n successful_folds = 0\n \n # Loop over requested folds only\n for fold in folds_to_use:\n print(f\"\\nProcessing Fold {fold}...\")\n # Load model for this fold\n model_dir = CFG.MODEL_DIR\n backbone_path = getattr(CFG, 'BACKBONE_PATH', None)\n model = BiomassModel(CFG.MODEL_NAME, pretrained=False, backbone_path=backbone_path)\n \n # Load weights\n weight_path = os.path.join(model_dir, f'best_model_fold{fold}.pth')\n if not os.path.exists(weight_path):\n print(f\"Warning: Model file {weight_path} not found! Skipping fold {fold}.\")\n del model\n torch.cuda.empty_cache(); gc.collect()\n continue\n \n state = torch.load(weight_path, map_location='cpu')\n # Handle state dict keys if necessary (e.g. if saved with 'model_state_dict' key)\n if isinstance(state, dict) and ('model_state_dict' in state or 'state_dict' in state):\n key = 'model_state_dict' if 'model_state_dict' in state else 'state_dict'\n sd = state[key]\n else:\n sd = state\n \n model.load_state_dict(sd)\n model.to(CFG.DEVICE)\n model.eval()\n \n # Run inference for this fold\n for i, (left, right, filename) in enumerate(tqdm(loader, desc=f\"Fold {fold}\")):\n # left and right are batches of size 1, convert to numpy for TTA function\n left_np = left[0].numpy()\n right_np = right[0].numpy()\n \n # Predict\n pred = predict_with_tta(model, left_np, right_np, tta_transforms)\n accumulated_preds[i] += pred\n \n successful_folds += 1\n # Cleanup model to save memory\n del model\n torch.cuda.empty_cache(); gc.collect()\n \n if successful_folds == 0:\n raise FileNotFoundError(f\"No model weights found for requested folds: {folds_to_use}\")\n\n # Average predictions over the number of successfully loaded folds\n final_predictions = accumulated_preds / successful_folds\n \n print(f\"\\nInference complete. Successfully used {successful_folds} fold(s) out of {len(folds_to_use)} requested.\")\n return final_predictions, filenames\n\n# ===============================================================\n# 9. POST-PROCESS PREDICTIONS\n# ===============================================================\ndef postprocess_predictions(preds_direct):\n \"\"\"\n Calculate derived targets from direct predictions.\n \n Input: (n_samples, 3) array with [total, gdm, green]\n Output: (n_samples, 5) array with [green, dead, clover, gdm, total]\n \"\"\"\n print(\"\\nPost-processing predictions...\")\n \n # Extract direct predictions\n pred_total = preds_direct[:, 0]\n pred_gdm = preds_direct[:, 1]\n pred_green = preds_direct[:, 2]\n \n # Calculate derived targets with non-negativity constraint\n pred_clover = np.maximum(0, pred_gdm - pred_green)\n pred_dead = np.maximum(0, pred_total - pred_gdm)\n \n # Stack in the order of ALL_TARGET_COLS\n # ['Dry_Green_g', 'Dry_Dead_g', 'Dry_Clover_g', 'GDM_g', 'Dry_Total_g']\n preds_all = np.stack([\n pred_green,\n pred_dead,\n pred_clover,\n pred_gdm,\n pred_total\n ], axis=1)\n \n print(f\"✓ Post-processing complete\")\n print(f\" Output shape: {preds_all.shape}\")\n print(f\"\\nPrediction statistics:\")\n for i, col in enumerate(CFG.ALL_TARGET_COLS):\n print(f\" {col:15s}: mean={preds_all[:, i].mean():.2f}, \"\n f\"std={preds_all[:, i].std():.2f}, \"\n f\"min={preds_all[:, i].min():.2f}, \"\n f\"max={preds_all[:, i].max():.2f}\")\n \n return preds_all\n\n\n# ===============================================================\n# 10. CREATE SUBMISSION FILE (FIXED)\n# ===============================================================\ndef create_submission(predictions, filenames):\n \"\"\"\n Create submission file in the required format.\n \n Args:\n predictions: (n_images, 5) array with all target predictions\n filenames: list of test image filenames\n \"\"\"\n print(\"\\n\" + \"=\"*70)\n print(\"CREATING SUBMISSION FILE\")\n print(\"=\"*70)\n \n # Step 0: Load test.csv first to check the image_path format\n test_df = pd.read_csv(CFG.TEST_CSV)\n print(f\"\\nTest CSV loaded: {len(test_df)} rows\")\n print(f\"Sample image_path from test.csv: {test_df['image_path'].iloc[0]}\")\n print(f\"Sample filename from predictions: {filenames[0]}\")\n \n # Step 1: Fix image_path format to match test.csv\n # If test.csv has \"test/ID123.jpg\" but we have \"ID123.jpg\", add the prefix\n test_path_example = test_df['image_path'].iloc[0]\n if '/' in test_path_example:\n # Extract the subdirectory prefix (e.g., \"test/\")\n prefix = test_path_example.rsplit('/', 1)[0] + '/'\n corrected_filenames = [prefix + fn for fn in filenames]\n print(f\"Corrected path format: {corrected_filenames[0]}\")\n else:\n corrected_filenames = filenames\n \n # Step 2: Create wide-format DataFrame with corrected paths\n preds_wide = pd.DataFrame(predictions, columns=CFG.ALL_TARGET_COLS)\n preds_wide.insert(0, 'image_path', corrected_filenames)\n \n print(f\"\\nWide format predictions:\")\n print(preds_wide.head())\n \n # Step 3: Convert to long format (melt)\n preds_long = preds_wide.melt(\n id_vars=['image_path'],\n value_vars=CFG.ALL_TARGET_COLS,\n var_name='target_name',\n value_name='target'\n )\n \n print(f\"\\nLong format predictions (first 10 rows):\")\n print(preds_long.head(10))\n \n # Step 4: Debug the merge\n print(f\"\\nDebug: Checking if paths match...\")\n print(f\"Unique paths in test_df: {test_df['image_path'].nunique()}\")\n print(f\"Unique paths in preds_long: {preds_long['image_path'].nunique()}\")\n \n common_paths = set(test_df['image_path'].unique()) & set(preds_long['image_path'].unique())\n print(f\"Common paths found: {len(common_paths)}\")\n \n if len(common_paths) == 0:\n print(\"\\n❌ ERROR: No matching paths found!\")\n print(f\"Test CSV paths sample: {list(test_df['image_path'].unique()[:3])}\")\n print(f\"Prediction paths sample: {list(preds_long['image_path'].unique()[:3])}\")\n raise ValueError(\"Path mismatch between test.csv and predictions\")\n \n # Step 5: Merge to get sample_ids\n submission = pd.merge(\n test_df[['sample_id', 'image_path', 'target_name']],\n preds_long,\n on=['image_path', 'target_name'],\n how='left'\n )\n \n # Step 6: Keep only required columns\n submission = submission[['sample_id', 'target']]\n \n # Step 7: Check for missing values\n missing_count = submission['target'].isna().sum()\n if missing_count > 0:\n print(f\"\\n⚠ Warning: {missing_count} missing predictions found!\")\n print(\"Sample missing entries:\")\n print(submission[submission['target'].isna()].head())\n submission.loc[submission['target'].isna(), 'target'] = 0.0\n \n # Step 8: Sort by sample_id\n submission = submission.sort_values('sample_id').reset_index(drop=True)\n \n # Step 9: Save to CSV\n output_path = os.path.join(CFG.SUBMISSION_DIR, 'submission70.csv')\n submission.to_csv(output_path, index=False)\n \n print(f\"\\n✓ Submission file saved: {output_path}\")\n print(f\" Total rows: {len(submission)}\")\n print(f\"\\nPrediction statistics:\")\n print(f\" Min: {submission['target'].min():.4f}\")\n print(f\" Max: {submission['target'].max():.4f}\")\n print(f\" Mean: {submission['target'].mean():.4f}\")\n print(f\" Non-zero values: {(submission['target'] > 0).sum()}/{len(submission)}\")\n \n print(f\"\\nFirst 10 rows:\")\n print(submission.head(10))\n print(f\"\\nLast 10 rows:\")\n print(submission.tail(10))\n \n # Step 10: Validation checks\n print(f\"\\n\" + \"=\"*70)\n print(\"VALIDATION CHECKS\")\n print(\"=\"*70)\n print(f\"✓ Expected rows: {len(test_df)}\")\n print(f\"✓ Actual rows: {len(submission)}\")\n print(f\"✓ Match: {len(submission) == len(test_df)}\")\n print(f\"✓ No missing values: {not submission['target'].isna().any()}\")\n print(f\"✓ All sample_ids unique: {submission['sample_id'].is_unique}\")\n print(f\"✓ Has non-zero predictions: {(submission['target'] > 0).any()}\")\n \n return submission\n\n# Create submission\n# Post-process predictions\n# Run inference\nif CFG.CREATE_SUBMISSION:\n predictions_direct, test_filenames = run_inference()\n predictions_all = postprocess_predictions(predictions_direct)\n submission_df = create_submission(predictions_all, test_filenames)","metadata":{"papermill":{"duration":0.015528,"end_time":"2026-01-05T05:09:15.754447","exception":false,"start_time":"2026-01-05T05:09:15.738919","status":"completed"},"tags":[],"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:20:42.524248Z","iopub.execute_input":"2026-01-27T18:20:42.524494Z","iopub.status.idle":"2026-01-27T18:23:25.828361Z","shell.execute_reply.started":"2026-01-27T18:20:42.524475Z","shell.execute_reply":"2026-01-27T18:23:25.827615Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport os\n\n# =============================================================================\n# CONFIGURATION\n# =============================================================================\n# Weights for the ensemble (Must sum to 1.0)\n# Adjust based on which model had better local CV or Public LB score.\n# Example: If Siglip was better, give it 0.6.\nW_SIGLIP = 0.25 # 0.35\nW_DINO = 0.75 # 0.65\n\nFILES = {\n 'siglip': 'submission70.csv',\n 'dino': 'submission72.csv'\n}\n\nOUTPUT_FILE = 'submission.csv'\n\n# Target definitions required for Mass Balance\nALL_TARGETS = ['Dry_Green_g', 'Dry_Clover_g', 'Dry_Dead_g', 'GDM_g', 'Dry_Total_g']\n\n# =============================================================================\n# HELPER FUNCTIONS\n# =============================================================================\n\ndef enforce_mass_balance(df_wide, fixed_clover=None):\n \"\"\"\n Applies Orthogonal Projection to enforce biological constraints:\n 1. Dry_Green_g + Dry_Clover_g = GDM_g\n 2. GDM_g + Dry_Dead_g = Dry_Total_g\n \n If fixed_clover is True, Dry_Clover_g is kept fixed and only other targets are adjusted.\n \n This finds the closest set of values to the predictions that satisfy \n the constraints (minimizing Euclidean distance modification).\n \"\"\"\n # 1. Ensure columns are in the specific order for the matrix math\n # Vector x = [Green, Clover, Dead, GDM, Total]\n ordered_cols = ['Dry_Green_g', 'Dry_Clover_g', 'Dry_Dead_g', 'GDM_g', 'Dry_Total_g']\n \n # Extract values: Shape (5, N_samples)\n Y = df_wide[ordered_cols].values.T\n \n if fixed_clover:\n # Keep Dry_Clover_g fixed, adjust only other targets\n # We have: Green + Clover_fixed = GDM, so GDM = Green + Clover_fixed\n # And: GDM + Dead = Total, so Total = GDM + Dead = Green + Clover_fixed + Dead\n # Extract fixed Clover values\n clover_fixed = Y[1, :].copy() # Dry_Clover_g is index 1\n # Adjust: GDM = Green + Clover_fixed\n Y[3, :] = Y[0, :] + clover_fixed # GDM_g\n # Adjust: Total = GDM + Dead = Green + Clover_fixed + Dead\n Y[4, :] = Y[3, :] + Y[2, :] # Dry_Total_g\n # Keep Green and Dead as is (or apply minimal adjustment if needed)\n # Clover stays fixed (already set)\n Y_reconciled = Y\n else:\n # Original method: adjust all targets\n # 2. Define Constraint Matrix C where Cx = 0\n # Eq 1: 1*Gr + 1*Cl + 0*De - 1*GDM + 0*Tot = 0\n # Eq 2: 0*Gr + 0*Cl + 1*De + 1*GDM - 1*Tot = 0\n C = np.array([\n [1, 1, 0, -1, 0],\n [0, 0, 1, 1, -1]\n ])\n \n # 3. Calculate Projection Matrix P = I - C^T * (C * C^T)^-1 * C\n C_T = C.T\n try:\n inv_CCt = np.linalg.inv(C @ C_T)\n P = np.eye(5) - C_T @ inv_CCt @ C\n except np.linalg.LinAlgError:\n # Fallback if singular (unlikely with this specific matrix)\n print(\"Warning: Singular matrix in projection. Skipping constraint enforcement.\")\n return df_wide\n\n # 4. Apply Projection\n Y_reconciled = P @ Y\n \n # 5. Transpose back to (N_samples, 5) and clip negatives\n Y_reconciled = Y_reconciled.T\n Y_reconciled = np.maximum(0, Y_reconciled) \n \n # 6. Update DataFrame\n df_out = df_wide.copy()\n df_out[ordered_cols] = Y_reconciled\n \n return df_out\n\ndef robust_ensemble(file_paths, weights):\n print(f\"--- Starting Ensemble ---\")\n print(f\"Weights: {weights}\")\n print(\"NOTE: Using DINO-only for Dry_Clover_g (better detection)\")\n \n dfs = []\n for name, path in file_paths.items():\n if not os.path.exists(path):\n raise FileNotFoundError(f\"Missing file: {path}\")\n \n # Read and sort by sample_id to ensure alignment\n df = pd.read_csv(path).sort_values('sample_id').reset_index(drop=True)\n dfs.append(df)\n print(f\"Loaded {name}: {len(df)} rows\")\n\n # 1. Check alignment\n base_ids = dfs[0]['sample_id']\n if not all(df['sample_id'].equals(base_ids) for df in dfs[1:]):\n raise ValueError(\"Sample IDs do not match between submission files!\")\n\n # 2. Split by target_name to handle Dry_Clover_g separately\n # Split sample_id into image_id and target_name\n dfs_split = []\n for df in dfs:\n df_split = df.copy()\n df_split[['image_id', 'target_name']] = df_split['sample_id'].str.rsplit('__', n=1, expand=True)\n dfs_split.append(df_split)\n \n # Get DINO and SigLIP dataframes (identify by order in file_paths)\n dino_idx = list(file_paths.keys()).index('dino')\n siglip_idx = list(file_paths.keys()).index('siglip')\n dino_df = dfs_split[dino_idx]\n siglip_df = dfs_split[siglip_idx]\n \n # 3. Separate targets: Dry_Clover_g uses DINO only, others use ensemble\n ensemble_results = []\n \n for target in ALL_TARGETS:\n # Filter for this target\n dino_target = dino_df[dino_df['target_name'] == target].copy()\n siglip_target = siglip_df[siglip_df['target_name'] == target].copy()\n \n if target == 'Dry_Clover_g':\n # Use DINO only for Clover\n print(f\"Using DINO-only for {target}\")\n ensemble_results.append(dino_target[['sample_id', 'target']])\n else:\n # Ensemble for other targets\n # Merge on sample_id to align\n merged = pd.merge(\n dino_target[['sample_id', 'target']].rename(columns={'target': 'dino_pred'}),\n siglip_target[['sample_id', 'target']].rename(columns={'target': 'siglip_pred'}),\n on='sample_id'\n )\n \n # Weighted average\n w_vec = np.array([weights['dino'], weights['siglip']])\n w_vec = w_vec / w_vec.sum()\n \n merged['target'] = merged['dino_pred'] * w_vec[0] + merged['siglip_pred'] * w_vec[1]\n ensemble_results.append(merged[['sample_id', 'target']])\n \n # 4. Combine all targets\n ensemble_df = pd.concat(ensemble_results, ignore_index=True)\n print(\"Weighted average complete (DINO-only for Clover).\")\n\n # 5. Prepare for Mass Balance (Convert Long -> Wide)\n ensemble_df[['image_id', 'target_name']] = ensemble_df['sample_id'].str.rsplit('__', n=1, expand=True)\n \n # Pivot\n wide_df = ensemble_df.pivot(index='image_id', columns='target_name', values='target').reset_index()\n\n # 6. Apply Robust Constraints (with Dry_Clover_g fixed)\n print(\"Applying Mass Balance Constraints (Dry_Clover_g fixed to DINO values)...\")\n wide_balanced = enforce_mass_balance(wide_df, fixed_clover=True)\n\n # 7. Convert back (Wide -> Long)\n long_balanced = wide_balanced.melt(\n id_vars='image_id', \n value_vars=ALL_TARGETS,\n var_name='target_name',\n value_name='target'\n )\n\n # Reconstruct sample_id\n long_balanced['sample_id'] = long_balanced['image_id'] + '__' + long_balanced['target_name']\n\n # 8. Final Formatting\n final_submission = long_balanced[['sample_id', 'target']].sort_values('sample_id').reset_index(drop=True)\n\n return final_submission\n\n# =============================================================================\n# EXECUTION\n# =============================================================================\nif __name__ == \"__main__\":\n \n # Define weights\n ensemble_weights = {\n 'siglip': W_SIGLIP,\n 'dino': W_DINO\n }\n \n try:\n # Run Ensemble\n submission = robust_ensemble(FILES, ensemble_weights)\n \n # Save\n submission.to_csv(OUTPUT_FILE, index=False)\n print(f\"\\nSuccess! Saved to {OUTPUT_FILE}\")\n print(submission.head())\n \n # Sanity Check Stats\n print(\"\\nStats:\")\n print(submission['target'].describe())\n \n except Exception as e:\n print(f\"\\nError during ensembling: {e}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-01-27T18:23:25.829483Z","iopub.execute_input":"2026-01-27T18:23:25.830006Z","iopub.status.idle":"2026-01-27T18:23:25.889362Z","shell.execute_reply.started":"2026-01-27T18:23:25.82998Z","shell.execute_reply":"2026-01-27T18:23:25.888651Z"}},"outputs":[],"execution_count":null}]}