Delete testpklfiles.py

testpklfiles.py

@@ -1,79 +0,0 @@
-# generate_pickles.py
-
-import pandas as pd
-import numpy as np
-import pickle
-import streamlit as st
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import LabelEncoder, StandardScaler
-from xgboost import XGBClassifier
-
-st.title("📦 Data Preprocessing and Pickle Saver")
-
-@st.cache_data
-def load_sampled_data():
-    df3 = pd.read_parquet("train_series.parquet", columns=['series_id', 'step', 'anglez', 'enmo'])
-    df4 = pd.read_parquet("test_series.parquet", columns=['series_id', 'step', 'anglez', 'enmo'])
-    df2 = pd.read_csv("train_events.csv")
-
-    # Sample safely based on available data
-    df3_sample = df3.sample(n=min(5_000_000, len(df3)), random_state=42)
-    df4_sample = df4.sample(n=min(1_000_000, len(df4)), random_state=42)
-
-    return df3_sample, df4_sample, df2
-
-# Load
-df3, df4, df2 = load_sampled_data()
-df = pd.concat([df3, df4], axis=0, ignore_index=True)
-merged_df = pd.merge(df, df2, on=['series_id', 'step'], how='inner')
-
-# Rename timestamp columns if they exist
-if 'timestamp_x' in merged_df.columns:
-    merged_df.rename(columns={'timestamp_x': 'sensor_timestamp'}, inplace=True)
-if 'timestamp_y' in merged_df.columns:
-    merged_df.rename(columns={'timestamp_y': 'event_timestamp'}, inplace=True)
-
-# Drop only columns that exist
-required_cols = ['night', 'event', 'event_timestamp']
-existing_cols = [col for col in required_cols if col in merged_df.columns]
-merged_df.dropna(subset=existing_cols, inplace=True)
-merged_df.reset_index(drop=True, inplace=True)
-
-# Convert timestamps and calculate sleep duration
-if 'event_timestamp' in merged_df.columns and 'sensor_timestamp' in merged_df.columns:
-    merged_df['event_timestamp'] = pd.to_datetime(merged_df['event_timestamp'], errors='coerce', utc=True)
-    merged_df['sensor_timestamp'] = pd.to_datetime(merged_df['sensor_timestamp'], errors='coerce', utc=True)
-    merged_df['sleep_duration_hrs'] = (merged_df['sensor_timestamp'] - merged_df['event_timestamp']).dt.total_seconds() / 3600
-    merged_df.dropna(subset=['sensor_timestamp', 'event_timestamp', 'sleep_duration_hrs'], inplace=True)
-
-# Encode
-le = LabelEncoder()
-merged_df['series_id'] = le.fit_transform(merged_df['series_id'])
-merged_df['event'] = le.fit_transform(merged_df['event'])
-
-# Drop columns with string or datetime values
-drop_cols = ['sensor_timestamp', 'event_timestamp', 'night', 'step', 'sleep_duration_hrs', 'series_id']
-df_cleaned = merged_df.drop(columns=[col for col in drop_cols if col in merged_df.columns])
-
-# Ensure only numeric features in X
-X = df_cleaned.drop('event', axis=1).select_dtypes(include=[np.number])
-y = merged_df['event']
-
-# Split and scale
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=27)
-scaler = StandardScaler()
-X_train_scaled = scaler.fit_transform(X_train)
-X_test_scaled = scaler.transform(X_test)
-
-# Train model
-model = XGBClassifier(n_estimators=100, max_depth=3, learning_rate=0.1, eval_metric='logloss')
-model.fit(X_train_scaled, y_train)
-
-# Save pickles
-with open("model.pkl", "wb") as f: pickle.dump(model, f)
-with open("scaler.pkl", "wb") as f: pickle.dump(scaler, f)
-with open("label_encoder.pkl", "wb") as f: pickle.dump(le, f)
-with open("X_test.pkl", "wb") as f: pickle.dump(X_test_scaled, f)
-with open("y_test.pkl", "wb") as f: pickle.dump(y_test, f)
-
-st.success("✅ Pickle files saved successfully.")