user-churn / utils /modelling.py
VasithaTilakumara
Version 2.0 - added LFS tracking for lsapp.tsv and updated features
53b92fc
Raw History Blame Contribute Delete
3.98 kB
import pandas as pd
import joblib
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, roc_auc_score, confusion_matrix, classification_report
from utils.data_prep import split_app
def train_models(X_train, y_train):
rf = RandomForestClassifier(n_estimators=200, max_depth=10, random_state=42)
lr = LogisticRegression(max_iter=1000, solver="liblinear")
rf.fit(X_train, y_train)
lr.fit(X_train, y_train)
return {"RandomForest": rf, "LogisticRegression": lr}
def evaluate_model(model, X_test, y_test):
y_pred = model.predict(X_test)
y_prob = model.predict_proba(X_test)[:, 1]
acc = accuracy_score(y_test, y_pred)
auc = roc_auc_score(y_test, y_prob)
cm = confusion_matrix(y_test, y_pred)
report = classification_report(y_test, y_pred, output_dict=True)
return {"accuracy": acc, "auc": auc, "cm": cm, "report": report}
# def add_churn_probability(app_df, model=None):
# X = app_df[["session_count", "recency"]]
# y = app_df["churn"]
# X_train, X_test, y_train, y_test = train_test_split(
# X, y, test_size=0.3, random_state=42, stratify=y
# )
# # X_train, X_test, y_train, y_test = split_app(app_df)
# # Train simple model
# # model = RandomForestClassifier(n_estimators=100, random_state=42)
# # model.fit(X_train, y_train)
# if model is None:
# model = RandomForestClassifier(n_estimators=100, random_state=42)
# model.fit(X_train, y_train)
# # Predict churn probability on holdout
# probs = model.predict_proba(X_test)[:, 1]
# # Build new df for plotting
# df_plot = X_test.copy()
# # df_plot["userid"] = app_df.loc[X_test.index, "userid"].values
# # df_plot["recency"] =
# df_plot["ChurnProbability"] = probs
# return df_plot
def train_and_predict_with_features(df, feature_cols, target_col="churn", model_out="models/rf_app.pkl", csv_out="results/appdata_rf.csv"):
"""
Trains a RandomForest model, predicts churn and probabilities,
and returns a dataframe that merges predictions with original features.
"""
X = df[feature_cols]
y = df[target_col]
# Split
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.3, random_state=42, stratify=y
)
# Scale
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
# Train RF
rf = RandomForestClassifier(n_estimators=200, max_depth=10, random_state=42)
rf.fit(X_train_scaled, y_train)
# Save model
# joblib.dump(rf, model_out)
# Predictions
churn_pred = rf.predict(X_test_scaled)
churn_prob = rf.predict_proba(X_test_scaled)[:, 1]
# Convert back to DataFrame
X_test_df = pd.DataFrame(X_test_scaled,
columns=[f"{c}_scaled" for c in feature_cols],
index=y_test.index)
churn_pred_series = pd.Series(churn_pred, index=X_test_df.index, name="PredictedChurn")
churn_prob_series = pd.Series(churn_prob, index=X_test_df.index, name="ChurnProbability")
# Join predictions with scaled features
df_preds = X_test_df.copy()
df_preds["TrueLabel"] = y_test
df_preds = df_preds.join(churn_pred_series).join(churn_prob_series)
# Merge with original unscaled features for interpretability
original_features_test = df.loc[X_test_df.index, feature_cols]
predictions_with_features = pd.concat(
[original_features_test.reset_index(drop=True), df_preds.reset_index(drop=True)],
axis=1
)
# Save results
# predictions_with_features.to_csv(csv_out, index=False)
return predictions_with_features
def save_model(model, path):
joblib.dump(model, path)
def load_model(path):
return joblib.load(path)