Spaces:
Runtime error
Runtime error
| import pandas as pd | |
| import numpy as np | |
| import os | |
| import joblib | |
| from sklearn.model_selection import train_test_split | |
| from sklearn.preprocessing import StandardScaler, LabelEncoder | |
| from sklearn.impute import SimpleImputer | |
| def resolve_model_dir(): | |
| base_dir = os.path.dirname(os.path.abspath(__file__)) | |
| candidates = [ | |
| os.path.join(base_dir, '..', 'model'), | |
| os.path.join(base_dir, 'model'), | |
| '/app/model' | |
| ] | |
| for p in candidates: | |
| if os.path.exists(p): | |
| return os.path.abspath(p) | |
| return os.path.abspath(candidates[0]) | |
| def resolve_data_path(): | |
| base_dir = os.path.dirname(os.path.abspath(__file__)) | |
| candidates = [ | |
| os.path.join(base_dir, '..', 'data', 'patient_dataset.csv'), | |
| os.path.join(base_dir, 'data', 'patient_dataset.csv'), | |
| os.path.join(base_dir, 'patient_dataset.csv'), | |
| '/app/data/patient_dataset.csv' | |
| ] | |
| for p in candidates: | |
| if os.path.exists(p): | |
| return os.path.abspath(p) | |
| return os.path.abspath(candidates[0]) | |
| # Canonical Column Alias Mapping | |
| COLUMN_ALIASES = { | |
| 'heart rate (bpm)': 'Heart Rate (bpm)', | |
| 'heart rate': 'Heart Rate (bpm)', | |
| 'heart_rate': 'Heart Rate (bpm)', | |
| 'heartrate': 'Heart Rate (bpm)', | |
| 'hr': 'Heart Rate (bpm)', | |
| 'spo2 level (%)': 'SpO2 Level (%)', | |
| 'spo2 level': 'SpO2 Level (%)', | |
| 'spo2_level': 'SpO2 Level (%)', | |
| 'spo2': 'SpO2 Level (%)', | |
| 'oxygen': 'SpO2 Level (%)', | |
| 'systolic blood pressure (mmhg)': 'Systolic Blood Pressure (mmHg)', | |
| 'systolic blood pressure': 'Systolic Blood Pressure (mmHg)', | |
| 'systolic_bp': 'Systolic Blood Pressure (mmHg)', | |
| 'systolic bp': 'Systolic Blood Pressure (mmHg)', | |
| 'sys_bp': 'Systolic Blood Pressure (mmHg)', | |
| 'systolic': 'Systolic Blood Pressure (mmHg)', | |
| 'diastolic blood pressure (mmhg)': 'Diastolic Blood Pressure (mmHg)', | |
| 'diastolic blood pressure': 'Diastolic Blood Pressure (mmHg)', | |
| 'diastolic_bp': 'Diastolic Blood Pressure (mmHg)', | |
| 'diastolic bp': 'Diastolic Blood Pressure (mmHg)', | |
| 'dia_bp': 'Diastolic Blood Pressure (mmHg)', | |
| 'diastolic': 'Diastolic Blood Pressure (mmHg)', | |
| 'body temperature (°c)': 'Body Temperature (°C)', | |
| 'body temperature': 'Body Temperature (°C)', | |
| 'body_temp': 'Body Temperature (°C)', | |
| 'temperature': 'Body Temperature (°C)', | |
| 'temp': 'Body Temperature (°C)', | |
| 'predicted disease': 'Predicted Disease', | |
| 'predicted_disease': 'Predicted Disease', | |
| 'disease': 'Predicted Disease', | |
| 'condition': 'Predicted Disease', | |
| 'diagnosis': 'Predicted Disease', | |
| 'label': 'Predicted Disease', | |
| } | |
| def preprocess_data(df, is_training=False, model_dir=None): | |
| if model_dir is None: | |
| model_dir = resolve_model_dir() | |
| os.makedirs(model_dir, exist_ok=True) | |
| scaler_path = os.path.join(model_dir, 'scaler.pkl') | |
| label_encoder_path = os.path.join(model_dir, 'label_encoder.pkl') | |
| imputer_path = os.path.join(model_dir, 'imputer.pkl') | |
| # 1. Normalize column names to canonical forms | |
| col_map = {} | |
| for col in df.columns: | |
| norm_key = str(col).strip().lower().replace('\ufffd', '°') | |
| if norm_key in COLUMN_ALIASES: | |
| col_map[col] = COLUMN_ALIASES[norm_key] | |
| elif isinstance(col, str) and '\ufffd' in col: | |
| col_map[col] = col.replace('\ufffd', '°') | |
| if col_map: | |
| df = df.rename(columns=col_map) | |
| columns_to_drop = ['Patient Number', 'Data Accuracy (%)', 'Heart Rate Alert', 'SpO2 Level Alert', 'Blood Pressure Alert', 'Temperature Alert', 'Fall Detection'] | |
| cols_drop = [c for c in columns_to_drop if c in df.columns] | |
| X_raw = df.drop(columns=cols_drop).copy() | |
| y = None | |
| if 'Predicted Disease' in X_raw.columns: | |
| y_raw = X_raw['Predicted Disease'] | |
| X_raw = X_raw.drop(columns=['Predicted Disease']) | |
| if is_training: | |
| label_encoder = LabelEncoder() | |
| y = label_encoder.fit_transform(y_raw) | |
| joblib.dump(label_encoder, label_encoder_path) | |
| joblib.dump(label_encoder.classes_, os.path.join(model_dir, 'classes.pkl')) | |
| else: | |
| if os.path.exists(label_encoder_path): | |
| try: | |
| label_encoder = joblib.load(label_encoder_path) | |
| y = label_encoder.transform(y_raw) | |
| except Exception: | |
| y = None | |
| else: | |
| y = y_raw | |
| # Ensure all canonical continuous features exist (defaults for missing inputs) | |
| defaults = { | |
| 'Heart Rate (bpm)': 75.0, | |
| 'SpO2 Level (%)': 98.0, | |
| 'Systolic Blood Pressure (mmHg)': 120.0, | |
| 'Diastolic Blood Pressure (mmHg)': 80.0, | |
| 'Body Temperature (°C)': 37.0, | |
| } | |
| for col, default_val in defaults.items(): | |
| if col not in X_raw.columns: | |
| X_raw[col] = default_val | |
| # Engineered Feature: Risk_Severity | |
| X_raw['Risk_Severity'] = (X_raw['Heart Rate (bpm)'] > 105).astype(int) + (X_raw['SpO2 Level (%)'] < 94).astype(int) | |
| continuous_features = ['Heart Rate (bpm)', 'SpO2 Level (%)', 'Systolic Blood Pressure (mmHg)', 'Diastolic Blood Pressure (mmHg)', 'Body Temperature (°C)', 'Risk_Severity'] | |
| if is_training: | |
| imputer = SimpleImputer(strategy='mean') | |
| X_raw[continuous_features] = imputer.fit_transform(X_raw[continuous_features]) | |
| joblib.dump(imputer, imputer_path) | |
| scaler = StandardScaler() | |
| X_raw[continuous_features] = scaler.fit_transform(X_raw[continuous_features]) | |
| joblib.dump(scaler, scaler_path) | |
| else: | |
| if os.path.exists(imputer_path): | |
| try: | |
| imputer = joblib.load(imputer_path) | |
| X_raw[continuous_features] = imputer.transform(X_raw[continuous_features]) | |
| except Exception: | |
| pass | |
| if os.path.exists(scaler_path): | |
| try: | |
| scaler = joblib.load(scaler_path) | |
| X_raw[continuous_features] = scaler.transform(X_raw[continuous_features]) | |
| except Exception: | |
| pass | |
| return X_raw, y | |
| def get_train_test_split(df): | |
| X, y = preprocess_data(df, is_training=True) | |
| return train_test_split(X, y, test_size=0.2, random_state=42, stratify=y) | |