diabetes model.py

# -*- coding: utf-8 -*-
"""
Created on Wed Jun 13 01:45:32 2018

@author: mahmoud
"""


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
diabetes = pd.read_csv('diabetes.csv')
print(diabetes.columns)

diabetes.head()
tempo12 = diabetes['Outcome']
tempo12.value_counts().plot(kind="bar")

print("dimension of diabetes data: {}".format(diabetes.shape))

print(diabetes.groupby('Outcome').size())


import seaborn as sns
sns.countplot(diabetes['Outcome'],label="Count")

diabetes.info()






from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(diabetes.loc[:, diabetes.columns != 'Outcome'], diabetes['Outcome'], stratify=diabetes['Outcome'], random_state=66)

from sklearn.linear_model import LogisticRegression 
model = LogisticRegression()
model.fit(X_train, y_train)

print("Accuracy on training set: {:.2f}".format(model.score(X_train, y_train)))
print("Accuracy on test set: {:.2f}".format(model.score(X_test, y_test)))


#Decision Tree

from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(random_state=0)
tree.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(tree.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(tree.score(X_test, y_test)))


tree = DecisionTreeClassifier(max_depth=3, random_state=0)
tree.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(tree.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(tree.score(X_test, y_test)))

print("Feature importances:\n{}".format(tree.feature_importances_))

#Random Forest


from sklearn.ensemble import RandomForestClassifier
rf = RandomForestClassifier(n_estimators=100, random_state=0)
rf.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(rf.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(rf.score(X_test, y_test)))


rf1 = RandomForestClassifier(max_depth=3, n_estimators=100, random_state=0)
rf1.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(rf1.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(rf1.score(X_test, y_test)))


#Support Vector Machine


from sklearn.svm import SVC
svc = SVC()
svc.fit(X_train, y_train)
print("Accuracy on training set: {:.2f}".format(svc.score(X_train, y_train)))
print("Accuracy on test set: {:.2f}".format(svc.score(X_test, y_test)))

###scaling
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.fit_transform(X_test)
svc = SVC()
svc.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.2f}".format(svc.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.2f}".format(svc.score(X_test_scaled, y_test)))




###############################################################################


###Deep Learning###



from sklearn.neural_network import MLPClassifier
mlp = MLPClassifier(random_state=42)
mlp.fit(X_train, y_train)
print("Accuracy on training set: {:.2f}".format(mlp.score(X_train, y_train)))
print("Accuracy on test set: {:.2f}".format(mlp.score(X_test, y_test)))


#$caling

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.fit_transform(X_test)
mlp = MLPClassifier(random_state=0)
mlp.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.3f}".format(
    mlp.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.3f}".format(mlp.score(X_test_scaled, y_test)))


#increase #of iterations

mlp = MLPClassifier(max_iter=1000, random_state=0)
mlp.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.3f}".format(
    mlp.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.3f}".format(mlp.score(X_test_scaled, y_test)))