# https://www.datacamp.com/tutorial/decision-tree-classification-python
# Load libraries
import pandas as pd
from sklearn.tree import DecisionTreeClassifier # Import Decision Tree Classifier
from sklearn.model_selection import train_test_split # Import train_test_split function
from sklearn import metrics #Import scikit-learn metrics module for accuracy calculation
from sklearn.tree import export_graphviz
from six import StringIO
from IPython.display import Image  
import pydotplus

import numpy as np

import warnings
warnings.filterwarnings("ignore")

col_names = ['pregnant', 'glucose', 'bp', 'skin', 'insulin', 'bmi', 'pedigree', 'age', 'label']
# load dataset
pima = pd.read_csv("diabetes.csv", header=None, names=col_names)

pima.head()



#split dataset in features and target variable
feature_cols = ['pregnant', 'insulin', 'bmi', 'age','glucose','bp','pedigree']
X = pima[feature_cols] # Features
y = pima.label # Target variable

# Split dataset into training set and test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)#, random_state=1) # 70% training and 30% test

# Create Decision Tree classifer object
clf = DecisionTreeClassifier(criterion="entropy",random_state=4)

# Train Decision Tree Classifer
clf = clf.fit(X_train,y_train)

#Predict the response for test dataset
y_pred = clf.predict(X_test)

# Model Accuracy, how often is the classifier correct?
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))






dot_data = StringIO()
export_graphviz(clf, out_file=dot_data,  
              filled=True, rounded=True,
                special_characters=True,feature_names = feature_cols,class_names=['0','1'])
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())  
graph.write_png('diabetes1.png')
Image(graph.create_png())



########################### SECOND EXAMPLE OPTIMIZING THE PERFORMANCE ####################


# Create Decision Tree classifer object
clf = DecisionTreeClassifier(criterion="entropy", max_depth=2,random_state=4)

# Train Decision Tree Classifer
clf = clf.fit(X_train,y_train)

#Predict the response for test dataset
y_pred = clf.predict(X_test)

# Model Accuracy, how often is the classifier correct?
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))


# test with a simplae vector
mine = np.array([[12, 13, 14, 23, 76, 5, 44]])
print(mine)

y_pred1 = clf.predict(mine)
print(y_pred1)




dot_data = StringIO()
export_graphviz(clf, out_file=dot_data,  
                filled=True, rounded=True,
                special_characters=True, feature_names = feature_cols,class_names=['0','1'])
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())  
graph.write_png('diabetes2.png')
Image(graph.create_png())