# import all necessary libraries

import pandas

from pandas.tools.plotting import scatter_matrix

from sklearn import cross_validation

from sklearn.metrics import matthews_corrcoef

from sklearn.metrics import classification_report

from sklearn.metrics import confusion_matrix

from sklearn.linear_model import LogisticRegression

from sklearn.tree import DecisionTreeClassifier

from sklearn.neighbors import KNeighborsClassifier

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

from sklearn.naive_bayes import GaussianNB

from sklearn.neural_network import MLPClassifier

from sklearn.preprocessing import MinMaxScaler

from sklearn.ensemble import GradientBoostingClassifier

from sklearn.metrics import accuracy_score

from sklearn import tree

# load the dataset (local path)

url = "data.csv"

# feature names

features = ["MDVP:Fo(Hz)","MDVP:Fhi(Hz)","MDVP:Flo(Hz)","MDVP:Jitter(%)","MDVP:Jitter(Abs)","MDVP:RAP","MDVP:PPQ","Jitter:DDP","MDVP:Shimmer","MDVP:Shimmer(dB)","Shimmer:APQ3","Shimmer:APQ5","MDVP:APQ","Shimmer:DDA","NHR","HNR","RPDE","DFA","spread1","spread2","D2","PPE","status"]

dataset = pandas.read_csv(url, names = features)

# store the dataset as an array for easier processing

array = dataset.values

scaler = MinMaxScaler(feature_range=(0,1))

scaled = scaler.fit_transform(array)

# X stores feature values

X = scaled[:,0:22]

# Y stores "answers", the flower species / class (every row, 4th column)

Y = scaled[:,22]

validation_size = 0.25

# randomize which part of the data is training and which part is validation

seed = 7

# split dataset into training set (80%) and validation set (20%)

X_train, X_validation, Y_train, Y_validation = cross_validation.train_test_split(X, Y, test_size = validation_size, random_state = seed)

# 10-fold cross validation to estimate accuracy (split data into 10 parts; use 9 parts to train and 1 for test)

num_folds = 10

num_instances = len(X_train)

seed = 7

# use the 'accuracy' metric to evaluate models (correct / total)

scoring = 'accuracy'

# algorithms / models

models = []

#models.append(('LR', LogisticRegression()))

#models.append(('LDA', LinearDiscriminantAnalysis()))

#models.append(('KNN', KNeighborsClassifier()))

models.append(('DT', DecisionTreeClassifier()))

#models.append(('NN', MLPClassifier(solver='lbfgs')))

#models.append(('NB', GaussianNB()))

#models.append(('GB', GradientBoostingClassifier(n_estimators=10000)))

# evaluate each algorithm / model

results = []

names = []

print("Scores for each algorithm:")

for name, model in models:

    kfold = cross_validation.KFold(n = num_instances, n_folds = num_folds, random_state = seed)

    cv_results = cross_validation.cross_val_score(model, X_train, Y_train, cv = kfold, scoring = scoring)

    results.append(cv_results)

    names.append(name)

    model.fit(X_train, Y_train)

    predictions = model.predict(X_validation)

    print(name, accuracy_score(Y_validation, predictions)*100)

    print(matthews_corrcoef(Y_validation, predictions))

    tree.export_graphviz(model, out_file="tree.dot")