finding corellation and plotting

scripts/logistic.py

@@ -4,11 +4,16 @@ from sklearn.linear_model import LogisticRegression
 from sklearn.preprocessing import LabelEncoder
 from sklearn.metrics import accuracy_score, classification_report
 import pickle
+import statsmodels.api as sm
+import matplotlib.pyplot as plt
+import seaborn as sns
 
 data = pd.read_excel('/Users/apple/Downloads/21092023-July_Sept.xlsx', sheet_name="op")
 data = data.dropna()
 print(data)
 
+data.plot()
+
 label_encoder = LabelEncoder()
 categorical_cols = ['Gender', 'Caste', 'Category', 'Marital Status', 'Blood Group']
 for col in categorical_cols:
@@ -17,6 +22,11 @@ for col in categorical_cols:
 X = data[['Age', 'Gender', 'Caste', 'Category', 'Marital Status']]
 y = data['Test Result']
 
+corr = X.corr()
+print(corr)
+sm.graphics.plot_corr(corr, xnames=list(corr.columns))
+plt.show()
+
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
 model = LogisticRegression()
@@ -26,6 +36,7 @@ y_pred = model.predict(X_test)
 
 accuracy = accuracy_score(y_test, y_pred)
 classification_report_result = classification_report(y_test, y_pred)
+#sns.heatmap(pd.DataFrame(classification_report_result).iloc[:-1, :].T, annot=True)
 
 print(f"Accuracy: {accuracy}")
 print("Classification Report:")
@@ -40,4 +51,4 @@ print(classification_report_result)
 
 # new_data = pd.DataFrame({'Age': [30], 'Gender': ['MALE'], 'Caste': ['SC'], 'Category': [''], 'Marital Status': ['Single']})
 # predicted_result = loaded_model.predict(new_data)
-# print(predicted_result)
+# print(predicted_result)