{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":116062,"databundleVersionId":14875579,"sourceType":"competition"},{"sourceId":290672964,"sourceType":"kernelVersion"}],"dockerImageVersionId":31234,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport gc\nimport pandas as pd\nimport numpy as np\nimport networkx as nx\nfrom tqdm.auto import tqdm\n\n# ==========================================\n# CONFIGURATION\n# ==========================================\nOBO_PATH = \"/kaggle/input/cafa-6-protein-function-prediction/Train/go-basic.obo\"\nSUBMISSION_INPUT = '/kaggle/input/cafa6-protein-function-enhanced-nb-v2/submission.tsv'\nSUBMISSION_OUTPUT = 'submission.tsv'\n\n# Threshold to remove weak noise.\nMIN_SCORE_THRESHOLD = 0.001 \n\n# ==========================================\n# 1. FAST GRAPH BUILDER (NetworkX)\n# ==========================================\ndef build_go_graph(go_obo_path):\n    print(f\"[1/4] Parsing OBO into DAG from {go_obo_path}...\")\n    go_graph = nx.DiGraph()\n    \n    if not os.path.exists(go_obo_path):\n        raise FileNotFoundError(f\"OBO not found: {go_obo_path}\")\n\n    with open(go_obo_path, \"r\") as f:\n        cur_id = None\n        for line in f:\n            line = line.strip()\n            if line == \"[Term]\":\n                cur_id = None\n            elif line.startswith(\"id: \"):\n                cur_id = line.split(\"id: \")[1].strip()\n                go_graph.add_node(cur_id)\n            elif line.startswith(\"is_a: \"):\n                pid = line.split()[1].strip()\n                if cur_id:\n                    go_graph.add_edge(cur_id, pid)\n            elif line.startswith(\"relationship: part_of \"):\n                parts = line.split()\n                if len(parts) >= 3:\n                    pid = parts[2].strip()\n                    if cur_id:\n                        go_graph.add_edge(cur_id, pid)\n\n    print(\"      -> Calculating Topological Order...\")\n    if not nx.is_directed_acyclic_graph(go_graph):\n        cycles = list(nx.simple_cycles(go_graph))\n        for cycle in cycles:\n            go_graph.remove_edge(cycle[0], cycle[1])\n\n    topo_order = list(nx.topological_sort(go_graph))\n    term_parents_map = {n: list(go_graph.successors(n)) for n in go_graph.nodes()}\n    \n    return topo_order, term_parents_map\n\n# ==========================================\n# 2. FAST PROPAGATION (HARD MAX)\n# ==========================================\ndef propagate_hard_max(df, topo_order, term_parents_map):\n    print(\"[3/4] Propagating Scores (Hard Max)...\")\n    print(\"      -> Grouping data...\")\n    \n    # Process by group to save memory and ensure isolation\n    groups = df.groupby('protein_id')\n    final_rows = []\n    \n    for pid, group in tqdm(groups):\n        # Map term -> score\n        scores = dict(zip(group['go_term'], group['score']))\n        \n        # Propagate from leaves to roots\n        for child in topo_order:\n            if child in scores:\n                child_score = scores[child]\n                if child in term_parents_map:\n                    for parent in term_parents_map[child]:\n                        current_parent_score = scores.get(parent, 0.0)\n                        # HARD MAX RULE: Parent score must be at least child score\n                        if child_score > current_parent_score:\n                            scores[parent] = child_score\n        \n        # Filter and collect\n        for term, score in scores.items():\n            if score >= MIN_SCORE_THRESHOLD:\n                final_rows.append((pid, term, score))\n\n    return pd.DataFrame(final_rows, columns=['protein_id', 'go_term', 'score'])\n\n# ==========================================\n# 3. MAIN PIPELINE\n# ==========================================\n\n# 1. Setup\ntopo_order, term_parents_map = build_go_graph(OBO_PATH)\n\nprint(f\"[2/4] Loading submission...\")\n# FIXED: names list now has 3 items to match your file\nsubmission = pd.read_csv(SUBMISSION_INPUT, sep='\\t', header=None, \n                         names=['protein_id', 'go_term', 'score'], \n                         dtype={'score': np.float32},\n                         on_bad_lines='skip') # Skip lines that don't match\n\n# 2. Propagate\nsubmission_improved = propagate_hard_max(submission, topo_order, term_parents_map)\n\n# 3. Save\nprint(f\"[4/4] Saving improved submission ({len(submission_improved)} rows)...\")\nsubmission_improved['score'] = submission_improved['score'].round(3)\nsubmission_improved.to_csv(SUBMISSION_OUTPUT, sep='\\t', index=False, header=False)\n\nprint(\"------------------------------------------------\")\nprint(f\"[Done] Saved to {SUBMISSION_OUTPUT}\")\nprint(\"------------------------------------------------\")\nprint(submission_improved.head())","metadata":{"_uuid":"5c0c722b-5c74-4b1b-af4a-6af4b307afb9","_cell_guid":"044f591b-13a3-4518-9726-55af338e9d0f","trusted":true,"collapsed":false,"jupyter":{"outputs_hidden":false}},"outputs":[],"execution_count":null}]}