MLP models

#checking version
import pandas as pd
import numpy as np
import scipy
import matplotlib
import sklearn
import sys
print('Python: {}'.format(sys.version))
print('numpy: {}'.format(sys.version))
print('scipy: {}'.format(sys.version))
print('matplotlib: {}'.format(sys.version))
print('sklearn: {}'.format(sys.version))

#importing dependencies
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
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.svm import SVC
from sklearn.ensemble import VotingClassifier


#Loading the data
# the data set is not connected by url,
#dimension and discription
print(iris.shape)
print(iris.describe())
#Class Discriptions
print(iris.groupby('class').size())
# box and visker plots
iris.plot(kind='box', subplots=True , layout=(2,2), sharex=False, sharey=False)
pyplot.show()
#histogram of the 
iris.hist()
pyplot.show()
#multivariate plots
scatter_matrix(iris)
pyplot.show()
#creating the data set
#sploitting the data to 70 30
array = iris.values
x = array[:,0:4]
y = array[:,4]
x_train, x_validation, y_train, y_validation = train_test_split(x,y,test_size=0.2, random_state=1)
#building models
#Logistic Regression    L
#K nearest neighbours  NL
#Linear discriminant analysis   L
#Classification and regression treee  NL
#GAussian Naive bayes  NL
#Support Vector Machines   nl


models = []
models.append(('LR',LogisticRegression(solver='liblinear', multi_class='ovr') ))
models.append(('LDA',LinearDiscriminantAnalysis()))
models.append(('KNN',KNeighborsClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC(gamma='auto')))

# the tenfold method
#its like the data will be splited into 10 parts and model trains on 9 parts and tests 1, and repeats it with each combination
results =[]
names = []
for name, model in models:
    kfold = StratifiedKFold(n_splits=10, random_state = 1)
    cv_results = cross_val_score(model, x_train, y_train, cv=kfold, scoring='accuracy')
    results.append(cv_results)
    names.append(name)
    print('%s %f (%f)' %(name,cv_results.mean(), cv_results.std()))
    
    
#compare the models
pyplot.boxplot(results, labels=names)
pyplot.title('Algorith brooo')
pyplot.show()

#make prediction as svc
model = SVC(gamma='auto')
model.fit(x_train, y_train)
predictions = model.predict(x_validation)
#evaluate our prediction
print(accuracy_score(y_validation, predictions))
print(confusion_matrix(y_validation, predictions))
print(classification_report(y_validation, predictions))