Upload 3 files

heart_disease_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b683e24bbf2a703692f163a49025058ad3f95ca433af9d2f5fe65f324921f0da
+size 998

heart_disease_model_training.py

@@ -0,0 +1,75 @@
+import numpy as np
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score
+import pickle
+
+heart_data = pd.read_csv(r'C:\Student\data/Copy of heart_disease_data.csv')
+# print first 5 rows of the dataset
+heart_data.head()
+heart_data.tail()
+# number of rows and columns in the dataset
+heart_data.shape
+# getting some info about the data
+heart_data.info()
+# checking for missing values
+heart_data.isnull().sum()
+# statistical measures about the data
+heart_data.describe()
+# checking the distribution of Target Variable
+heart_data['target'].value_counts()
+# 1 --> Defective Heart
+#0 --> Healthy Heart
+
+#Splitting the Features and Target
+X = heart_data.drop(columns='target', axis=1)
+Y = heart_data['target']
+print(X)
+print(Y)
+#Splitting the Data into Training data & Test Data
+X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, stratify=Y, random_state=2)
+print(X.shape, X_train.shape, X_test.shape)
+#Model Training
+
+#Logistic Regression
+model = LogisticRegression()
+# training the LogisticRegression model with Training data
+model.fit(X_train, Y_train)
+#Model Evaluation
+# Save the trained model to a pickle file
+with open('heart_disease_model.pkl', 'wb') as model_file:
+    pickle.dump(model, model_file)
+
+print("Model trained and saved as 'heart_disease_model.pkl'")
+
+# Load the saved model from the pickle file
+with open('heart_disease_model.pkl', 'rb') as model_file:
+    loaded_model = pickle.load(model_file)
+
+
+
+#Accuracy Score
+# accuracy on training data
+X_train_prediction = model.predict(X_train)
+training_data_accuracy = accuracy_score(X_train_prediction, Y_train)
+print('Accuracy on Training data : ', training_data_accuracy)
+# accuracy on test data
+X_test_prediction = model.predict(X_test)
+test_data_accuracy = accuracy_score(X_test_prediction, Y_test)
+print('Accuracy on Test data : ', test_data_accuracy)
+#Building a Predictive System
+input_data = (99,1,4,300,600,1,2,500,1,7.2,0,2,5)
+# change the input data to a numpy array
+input_data_as_numpy_array= np.asarray(input_data)
+
+# reshape the numpy array as we are predicting for only on instance
+input_data_reshaped = input_data_as_numpy_array.reshape(1,-1)
+
+prediction = model.predict(input_data_reshaped)
+print(prediction)
+
+if (prediction[0]== 0):
+  print('The Person does not have a Heart Disease')
+else:
+  print('The Person has Heart Disease')

requirements..txt

@@ -0,0 +1,5 @@
+pip
+streamlit
+numpy
+pandas
+sklearn