#including cv
import pandas as pd
import numpy as np
from sklearn.cross_validation import KFold

def read(path="./datasets/train.csv"):
    return(pd.read_csv(path, index_col='Date', parse_dates='Date'))

data=read()
cleanData=data[pd.notnull(data['Weight'])]

def cv(data=cleanData, n_folds=10):
    """split data in n_folds parts for cross validation
    """
    kf=KFold(len(data), shuffle=True, n_folds=n_folds)

    trainid=[]
    testid=[]
    for train, test in kf:
        trainid.append(train)
        testid.append(test)
    data_train=[]
    data_test=[]

    for i in range(n_folds):
        data_train.append(pd.DataFrame(data.iloc[j] for j in trainid[i]))
        data_test.append(pd.DataFrame(data.iloc[j] for j in testid[i]))
    return (data_train,data_test)

data_train, data_test=cv()

#print(data_test[0])