import pandas as pd
import numpy as np
heart_disease = pd.read_csv('data/heart.csv')
heart_disease.head()

# Create Features Matrix (X)
X = heart_disease.drop('target', axis=1)

# Create Labels (Y)
y = heart_disease['target']

from sklearn.ensemble import RandomForestClassifier
clf = RandomForestClassifier()
clf.get_params() # lists the hyperparameters

{'bootstrap': True,
 'ccp_alpha': 0.0,
 'class_weight': None,
 'criterion': 'gini',
 'max_depth': None,
 'max_features': 'auto',
 'max_leaf_nodes': None,
 'max_samples': None,
 'min_impurity_decrease': 0.0,
 'min_impurity_split': None,
 'min_samples_leaf': 1,
 'min_samples_split': 2,
 'min_weight_fraction_leaf': 0.0,
 'n_estimators': 100,
 'n_jobs': None,
 'oob_score': False,
 'random_state': None,
 'verbose': 0,
 'warm_start': False}

# fit the model to data
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.2) 
# Means 20% of the data will be used as testing data

clf.fit(X_train, y_train);

# make prediction
y_label = clf.predict(np.array([0,2,3,4]))

y_preds = clf.predict(X_test)
y_preds

array([1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0,
       1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0,
       1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1], dtype=int64)

y_test.head()

72     1
116    1
107    1
262    0
162    1
Name: target, dtype: int64

clf.score(X_train, y_train)

1.0

clf.score(X_test, y_test)

0.7704918032786885

from sklearn.metrics import classification_report, confusion_matrix, accuracy_score

print(classification_report(y_test, y_preds))

              precision    recall  f1-score   support

           0       0.77      0.71      0.74        28
           1       0.77      0.82      0.79        33

    accuracy                           0.77        61
   macro avg       0.77      0.77      0.77        61
weighted avg       0.77      0.77      0.77        61

print(confusion_matrix(y_test, y_preds))

[[20  8]
 [ 6 27]]

print(accuracy_score(y_test, y_preds))

0.7704918032786885

# Try different amount of n_estimators
np.random.seed(42)
for i in range(1, 100, 10):
    print(f'Trying model with {i} estimators')
    clf = RandomForestClassifier(n_estimators=i).fit(X_train, y_train)
    print(f'Model accuracy on test set: {clf.score(X_test, y_test) * 100:.2f}%')
    print('')

Trying model with 1 estimators
Model accuracy on test set: 72.13%

Trying model with 11 estimators
Model accuracy on test set: 83.61%

Trying model with 21 estimators
Model accuracy on test set: 78.69%

Trying model with 31 estimators
Model accuracy on test set: 78.69%

Trying model with 41 estimators
Model accuracy on test set: 75.41%

Trying model with 51 estimators
Model accuracy on test set: 75.41%

Trying model with 61 estimators
Model accuracy on test set: 75.41%

Trying model with 71 estimators
Model accuracy on test set: 73.77%

Trying model with 81 estimators
Model accuracy on test set: 73.77%

Trying model with 91 estimators
Model accuracy on test set: 75.41%

import pickle

pickle.dump(clf, open('random_forest_model_1.pkl', 'wb'))

#load the model
loaded_model = pickle.load(open('random_forest_model_1.pkl','rb'))
loaded_model.score(X_test, y_test)

0.7540983606557377