ml

# -*- coding: utf-8 -*-
"""
Created on Mon Apr 23 17:07:08 2018

@author: twixs
"""

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""

import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import KFold


data = pd.read_csv("C:\\Users\\twixs\\Desktop\\WS_MACHINE\\credit.csv")

def prepareDataForLearning(pandas_data, class_index):
    class_col = pandas_data.iloc[:, class_index]
    copy = pandas_data.copy(deep=True)
    copy = copy.drop(copy.columns[class_index], axis=1)
    return copy, class_col

#Split Data
inputData, expectedResult = prepareDataForLearning(data,15)

#Labelling
encoder = LabelEncoder()
eOutput = encoder.fit_transform(expectedResult)

iData = inputData.apply(encoder.fit_transform)


#Scaler

scaler = StandardScaler()
scaler.fit(iData)

iData = scaler.transform(iData)


#Kfold

nSamples = 10.0

kf=KFold(n_splits=int(nSamples))

#Create classifier
meanAccuracy=0

for train_index, test_index in kf.split(iData):


    clf = RandomForestClassifier(n_estimators=1, n_jobs=1, random_state=0)

    clf.fit(iData[train_index], eOutput[train_index])

    acc=clf.score(iData[test_index],eOutput[test_index])

    meanAccuracy += acc

print("Final Precision= ", (meanAccuracy/nSamples)*100)