{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":102335,"databundleVersionId":12518947,"sourceType":"competition"}],"dockerImageVersionId":31040,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"
\n
\n

Published on June 1, 2025

\n

Author: Jocelyn C. Dumlao

\n

\n LinkedIn\n GitHub\n YouTube\n Kaggle\n
\n
","metadata":{}},{"cell_type":"markdown","source":"
\n \"image\"\n
","metadata":{}},{"cell_type":"markdown","source":"#

πŸ”πŸ§ΎπŸ“€ Prediction and Submission

","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.preprocessing import LabelEncoder\nimport os\nimport polars as pl # Import Polars\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import f1_score\nimport kaggle_evaluation.cmi_inference_server # Import the inference server\nimport pyarrow.parquet as pq # Import parquet writing library\nimport pyarrow as pa\n\n# --- 1. Load and Train Model---\n# Load training data\ntrain_path = '/kaggle/input/cmi-detect-behavior-with-sensor-data/train.csv'\ntrain_demo_path = '/kaggle/input/cmi-detect-behavior-with-sensor-data/train_demographics.csv'\ntrain = pd.read_csv(train_path, nrows=10000) # Limiting the rows to 10000 for testing\ntrain_demo = pd.read_csv(train_demo_path)\ntrain = train.merge(train_demo, on=\"subject\", how=\"left\")\n\n# Encode gesture labels\nle = LabelEncoder()\ntrain['gesture_encoded'] = le.fit_transform(train['gesture'])\n\n# Features and target\nfeatures = ['acc_x', 'acc_y', 'acc_z', 'rot_w', 'rot_x', 'rot_y', 'rot_z']\nX = train[features]\ny = train['gesture_encoded']\n\n# Train model\nclf = RandomForestClassifier(n_estimators=100, random_state=42)\n\n# Split data\nX_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)\n\nclf.fit(X_train, y_train)\n\n\n# --- 2. Define the `predict` function ---\ndef predict(sequence: pl.DataFrame, demographics: pl.DataFrame) -> str:\n \"\"\"\n Predicts the gesture for a given sequence of sensor data.\n \"\"\"\n try:\n # Convert Polars DataFrames to Pandas for easier processing\n sequence = sequence.to_pandas()\n demographics = demographics.to_pandas()\n\n # Merge demographic info \n sequence = sequence.merge(demographics, on=\"subject\", how=\"left\")\n\n # Extract features\n X_test = sequence[features]\n\n # Predict gesture (encoded)\n gesture_encoded = clf.predict(X_test)[0] \n\n # Decode gesture\n gesture = le.inverse_transform([gesture_encoded])[0]\n\n return gesture\n except Exception as e:\n print(f\"Error in predict function: {e}\") # Log the error\n return \"Unknown\" # Or a default gesture\n\n# --- 3. Start the Inference Server ---\ninference_server = kaggle_evaluation.cmi_inference_server.CMIInferenceServer(predict)\n\nif os.getenv('KAGGLE_IS_COMPETITION_RERUN'):\n # Create an empty Pandas DataFrame with the required columns, DO NOT write to file.\n submission = pd.DataFrame(columns=['sequence_id', 'gesture']) #Dummy Dataframe\n\n # Serve the Inference Server (The server manages the submission creation).\n inference_server.serve()\nelse:\n inference_server.run_local_gateway(\n data_paths=(\n '/kaggle/input/cmi-detect-behavior-with-sensor-data/test.csv',\n '/kaggle/input/cmi-detect-behavior-with-sensor-data/test_demographics.csv',\n )\n )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-02T04:31:01.066923Z","iopub.execute_input":"2025-06-02T04:31:01.067280Z","iopub.status.idle":"2025-06-02T04:31:06.599105Z","shell.execute_reply.started":"2025-06-02T04:31:01.067255Z","shell.execute_reply":"2025-06-02T04:31:06.598048Z"}},"outputs":[],"execution_count":null}]}