barclays_challenge_event_20.../main.py

78 lines
2.2 KiB
Python

import models
import pandas as pd
import preprocessing as pp
from sklearn.metrics import accuracy_score
# Load Data
credit_risk = pd.read_csv("credit_risk_dataset.csv")
# Feature Addition
# Feature Conversion
person_home_ownership_values = {
"RENT": 1,
"MORTGAGE": 2,
"OWN": 3,
"OTHER": 4,
}
loan_intent_values = {
"EDUCATIONAL": 1,
"MEDICAL": 2,
"VENTURE": 3,
"PERSONAL": 4,
"DEBTCONSOLIDATION": 5
}
loan_grade_values = {
"A": 1,
"B": 2,
"C": 3,
"D": 4,
"E": 5
}
cb_person_default_on_file_values = {
"Y": 1,
"N": 0,
}
# Convert categorical column to a numerical column
credit_risk["person_home_ownership"] = credit_risk["person_home_ownership"].map(person_home_ownership_values)
credit_risk["loan_intent"] = credit_risk["loan_intent"].map(loan_intent_values)
credit_risk["loan_grade"] = credit_risk["loan_grade"].map(loan_grade_values)
credit_risk["cb_person_default_on_file"] = credit_risk["cb_person_default_on_file"].map(cb_person_default_on_file_values)
print("Feature Conversion Complete")
# Feature Removal
# columns_for_removal = ["housing_median_age", "total_rooms", "total_bedrooms"]
# for column in columns_for_removal:
# housing.drop(column, axis=1, inplace=True)
# Preprocessing
credit_risk = pp.impute_missing_values(credit_risk) # Handle missing values
print("Missing Values handling Complete")
# housing = pp.remove_outliers(housing) #Remove outliers
# Training and Testing Preperation
training_features, training_target_value, test_features, test_target_value = pp.training_test_split(credit_risk, "loan_status") # Split the data into Training and Test sets
print("Training and Test features split Complete")
# Normalise the data
training_features, test_features = pp.normalise(training_features,
test_features)
print("Normalisation Complete")
# Init Models
rf_model = models.random_forest_classifier(training_features,
training_target_value)
print("Model Init Complete")
# Get Predictions
rf_predictions = rf_model.predict(test_features)
print("Predictions Complete")
# Compare Results
accuracy = accuracy_score(test_target_value, rf_predictions)
print(f"Accuracy: {accuracy}")
print(rf_predictions)