File size: 1,314 Bytes
0914e96 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
import pandas as pd
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
import joblib
print("--- Starting Budget Predictor Model Training ---")
# 1. Data Load Karna
df = pd.read_csv('data/dummy_campaigns.csv')
# 2. Features aur Target ko Alag Karna
# Hum `final_reach` ke basis par `budget` predict karna seekhenge
X = df.drop('budget', axis=1)
y = df['budget']
# 3. Preprocessing (Text data ko numbers mein badalna)
categorical_features = ['category', 'location', 'platform']
preprocessor = ColumnTransformer(
transformers=[('cat', OneHotEncoder(handle_unknown='ignore'), categorical_features)],
remainder='passthrough'
)
# 4. Model Banana
model = GradientBoostingRegressor(n_estimators=100, random_state=42)
# 5. Full Pipeline Banana
pipeline = Pipeline(steps=[('preprocessor', preprocessor),
('regressor', model)])
# 6. Model ko Train Karna
pipeline.fit(X, y)
print("--- Model training complete. ---")
# 7. Trained Model ko Save Karna
model_path = 'models/budget_predictor_v1.joblib'
joblib.dump(pipeline, model_path)
print(f"--- Budget predictor model saved to {model_path} ---") |