Initial Commit

Author: pH-7

.gitignore

@@ -0,0 +1,9 @@
+*.pyc
+__pycache__/
+.env
+models/
+outputs/
+*.zip
+
+# Metadata OS files
+.DS_Store

README.md

@@ -0,0 +1,3 @@
+# GLM Learning Project
+
+This is a learning project to understand **Generalised Linear Models** (GLM) using Python.

data/sample.csv

@@ -0,0 +1,4 @@
+age,income,balance,default
+25,50000,2000,0
+45,80000,5000,1
+35,62000,3000,0

notebooks/GLM_Model_Exploration.ipynb

@@ -0,0 +1,7 @@
+pandas
+numpy
+statsmodels
+matplotlib
+seaborn
+scikit-learn
+jupyter

requirements.txt

@@ -0,0 +1,28 @@
+import pandas as pd
+import statsmodels.api as sm
+import matplotlib.pyplot as plt
+
+def load_data(filepath):
+    df = pd.read_csv(filepath)
+    return df
+
+def preprocess_data(df, target_col, feature_cols):
+    X = df[feature_cols]
+    X = sm.add_constant(X)
+    y = df[target_col]
+    return X, y
+
+def fit_glm(X, y, family=sm.families.Binomial()):
+    model = sm.GLM(y, X, family=family)
+    results = model.fit()
+    return results
+
+def main():
+    df = load_data("data/sample.csv")
+    X, y = preprocess_data(df, "default", ["age", "income", "balance"])
+    results = fit_glm(X, y)
+    print(results.summary())
+    results.save("models/glm_model.pickle")
+
+if __name__ == "__main__":
+    main()