Update engine_model.pkl

engine_model.pkl

@@ -1,38 +1,28 @@
 import pandas as pd
-import numpy as np
 import xgboost as xgb
 import joblib
 
-# 1. Download the dataset
+# Load the dataset directly from the web
 url = "https://raw.githubusercontent.com/datasets-machine-learning/nasa-turbofan-failure-prediction/master/data/train_FD001.txt"
 cols = ['unit', 'cycles', 'os1', 'os2', 'os3'] + [f's{i}' for i in range(1, 22)]
 df = pd.read_csv(url, sep='\s+', header=None, names=cols)
 
-# 2. Calculate Remaining Useful Life (RUL) - This is our 'Target'
-# We find the maximum cycle for each engine and subtract the current cycle
+# Calculate RUL (Remaining Useful Life)
 max_cycles = df.groupby('unit')['cycles'].max().reset_index()
 max_cycles.columns = ['unit', 'max_of_unit']
 df = df.merge(max_cycles, on='unit', how='left')
 df['RUL'] = df['max_of_unit'] - df['cycles']
 
-# 3. Feature Selection
-# We use the most important sensors for a jet engine
-features = ['cycles', 's2', 's3', 's4', 's7', 's8', 's11', 's12', 's13', 's15', 's17', 's20', 's21']
+# We use exactly 15 features to match the app.py logic
+# (cycles + 14 sensor/settings columns)
+features = ['cycles', 's2', 's3', 's4', 's7', 's8', 's11', 's12', 's13', 's15', 's17', 's20', 's21', 'os1', 'os2']
 X = df[features]
 y = df['RUL']
 
-# 4. Train the Model (XGBoost)
-print("Training the model... please wait.")
-model = xgb.XGBRegressor(
-    n_estimators=100, 
-    learning_rate=0.1, 
-    max_depth=5, 
-    objective='reg:squarederror'
-)
+# Train the model
+model = xgb.XGBRegressor(n_estimators=100, learning_rate=0.1)
 model.fit(X, y)
 
-# 5. Save the 'Brain' of the AI
+# SAVE THE FILE
 joblib.dump(model, 'engine_model.pkl')
-
-print("✅ Success! 'engine_model.pkl' has been created in your folder.")
-print("Now, upload this file to your Hugging Face Space.")
+print("✅ Done! 'engine_model.pkl' created in your folder.")