one

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9-SLIM
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,94 @@
+from fastapi import FastAPI, HTTPException
+import pandas as pd
+from pydantic import BaseModel
+import joblib
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.linear_model import LogisticRegression
+
+# Initialize FastAPI app
+app = FastAPI()
+
+# Load dataset
+DATASET_PATH = "credit_risk_dataset.csv"  # Update with actual dataset path
+df = pd.read_csv(DATASET_PATH)
+
+# Prepare data for ML training
+FEATURES = ["loan_amnt", "loan_int_rate", "person_age", "person_income", "cb_person_cred_hist_length"]
+X = df[FEATURES]
+y = df["loan_status"]
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Train models
+classifier = RandomForestClassifier(n_estimators=100, random_state=42)
+classifier.fit(X_train, y_train)
+joblib.dump(classifier, "models/risk_classifier.pkl")
+
+regressor = LogisticRegression()
+regressor.fit(X_train, y_train)
+joblib.dump(regressor, "models/past_due_regressor.pkl")
+
+# Load ML models
+classifier = joblib.load("models/risk_classifier.pkl")
+regressor = joblib.load("models/past_due_regressor.pkl")
+
+# Pydantic models for validation
+class LoanRequest(BaseModel):
+    loan_amnt: float
+    loan_int_rate: float
+    person_age: int
+    person_income: float
+    person_home_ownership: str
+    cb_person_cred_hist_length: int
+
+# API Endpoints
+@app.get("/loan_status_distribution")
+def loan_status_distribution():
+    if "loan_status" not in df.columns:
+        raise HTTPException(status_code=400, detail="Missing 'loan_status' column")
+    
+    status_counts = df["loan_status"].value_counts(normalize=True) * 100
+    return {"default_percentage": status_counts.get(1, 0), "non_default_percentage": status_counts.get(0, 0)}
+
+@app.get("/payment_timeline_analysis")
+def payment_timeline_analysis():
+    grouped = df.groupby("loan_status")["loan_amnt"].mean().to_dict()
+    return {"average_loan_amount_by_status": grouped}
+
+@app.get("/principal_amount_patterns")
+def principal_amount_patterns():
+    demographic_defaults = df.groupby(["person_age", "person_income", "person_home_ownership"])['loan_status'].mean().to_dict()
+    return {"demographic_default_rates": demographic_defaults}
+
+@app.get("/credit_history_impact")
+def credit_history_impact():
+    history_impact = df.groupby("cb_person_cred_hist_length")["loan_status"].mean().to_dict()
+    return {"credit_history_default_rates": history_impact}
+
+@app.get("/customer_profile_analysis")
+def customer_profile_analysis():
+    profile_analysis = df.groupby(["person_age", "person_income", "person_home_ownership"])["loan_status"].mean().to_dict()
+    return {"customer_profile_default_rates": profile_analysis}
+
+@app.get("/loan_intent_analysis")
+def loan_intent_analysis():
+    intent_defaults = df.groupby("loan_intent")["loan_status"].mean().to_dict()
+    return {"loan_intent_default_rates": intent_defaults}
+
+@app.get("/collection_effectiveness")
+def collection_effectiveness():
+    success_rate = df.groupby("cb_person_default_on_file")["loan_status"].mean().to_dict()
+    return {"collection_success_rate": success_rate}
+
+@app.get("/risk_score_development")
+def risk_score_development():
+    risk_factors = df.groupby(["loan_amnt", "loan_int_rate", "person_age", "person_income", "cb_person_cred_hist_length"])["loan_status"].mean().to_dict()
+    return {"risk_scores": risk_factors}
+
+@app.post("/predict_loan_risk")
+def predict_loan_risk(request: LoanRequest):
+    input_data = [[request.loan_amnt, request.loan_int_rate, request.person_age, request.person_income, request.cb_person_cred_hist_length]]
+    risk_class = classifier.predict(input_data)[0]
+    risk_prob = regressor.predict_proba(input_data)[0][1]
+    return {"predicted_risk_category": int(risk_class), "default_probability": float(risk_prob)}
+

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+pandas
+pydantic
+joblib
+scikit-learn