<Type2>540_train Data Preprocessing

import pandas as pd
import numpy as np
import h5py
import matplotlib
#matplotlib.use('agg')
import matplotlib.pyplot as plt
from keras.models import Model, Sequential
from keras.layers import Dense, Input, concatenate,Conv1D, Conv2D, MaxPooling2D, Conv2DTranspose,MaxPooling1D, Cropping2D, Multiply, subtract, Flatten, Reshape, Permute, LSTM, TimeDistributed,Dropout,BatchNormalization,UpSampling1D
from keras.optimizers import SGD
from keras.callbacks import ModelCheckpoint,EarlyStopping
import tensorflow as tf
from keras.models import load_model
from keras import optimizers
from keras import regularizers
from math import sqrt
from sklearn.metrics import mean_squared_error
from sklearn.metrics import mean_absolute_error
import pickle
from sklearn.preprocessing import StandardScaler
import time
from sklearn import preprocessing
from numpy import argmax
from keras.utils import to_categorical
from tabulate import tabulate
from numpy import array
from imblearn.over_sampling import SMOTE
from imblearn.combine import SMOTEENN
from collections import Counter

#import the data
#path="D:\\NCSU Research\\GEARS_Jul9\GEARS\\540\\x_train_540_final.pkl"
#data=np.load(path, allow_pickle=True) #1. path中\改为\\; 2. 加allow_pinckle=True

file_540=open("D:\\NCSU Research\\GEARS_Jul9\GEARS\\540\\x_train_540_final.pkl","rb")
data = pickle.load(file_540)
#print(data.isnull().any()) all false


#print(data)
#print(type(data))=<class 'pandas.core.frame.DataFrame'>
#same as using pd.load

#prepare data: (Emaily)prepare_data*: load in data with selected features, forward filling the missing value, and prepare the train, valid, test series for model usage
#feature selection(why: can check it later)
#pick_index=['glucose level','fingerstick','basis_gsr','basis_skintem','acceleration','basal','bolus','meal']

#make the data balenced
#add label to data
data["label"]=pd.cut(data["glucose level"], bins=[0,70,130,10000], labels=[-1,0,1])
#print(data)


#do balance by the label
#from imblearn.over_sampling import BorderlineSMOT
#切片：分开特征x和目标y
#X,y=data.["time" "fingerstick"  "basis_gsr"  "basis_skintem"  "acceleration"  "bolus"  "basal"  "meal"  "basis_sleep"]
#ros=BorderlineSMOTE(sampling_strategy={-1:3000,0:6000,1:})
#First I hope to use the pakage directly for resampleing
#However, I realize that there's a time series, which makes the order of data also important
#Therefore, I attempt to first rearange the data to run away from time series
#Or there's another way to deal with the imbalanced data which is to modify the loss function

#rearrange the data
#to delet the first, second, third...and combine them together
data_without=data.drop(labels=["time","glucose level"],axis=1,inplace=False)

data_0=data_without
data_0=data_0.reset_index(drop=True)


data_1=data_without.drop(data.index[0])
data_1.columns=["fingerstick_1", "basis_gsr_1", "basis_skintem_1", "acceleration_1", "bolus_1", "basal_1", "meal_1", "basis_sleep_1", "label_1"]
data_1=data_1.reset_index(drop=True) #after reseting will give a new dataframe
#print(data_1)
data_2=data_1.drop(data_1.index[0])
data_2.columns=["fingerstick_2", "basis_gsr_2", "basis_skintem_2", "acceleration_2", "bolus_2", "basal_2", "meal_2", "basis_sleep_2", "label_2"]
data_2=data_2.reset_index(drop=True)

data_3=data_2.drop(data_2.index[0])
data_3.columns=["fingerstick_3", "basis_gsr_3", "basis_skintem_3", "acceleration_3", "bolus_3", "basal_3", "meal_3", "basis_sleep_3", "label_3"]
data_3=data_3.reset_index(drop=True)

data_4=data_3.drop(data_3.index[0])
data_4.columns=["fingerstick_4", "basis_gsr_4", "basis_skintem_4", "acceleration_4", "bolus_4", "basal_4", "meal_4", "basis_sleep_4", "label_4"]
data_4=data_4.reset_index(drop=True)

data_5=data_4.drop(data_4.index[0])
data_5.columns=["fingerstick_5", "basis_gsr_5", "basis_skintem_5", "acceleration_5", "bolus_5", "basal_5", "meal_5", "basis_sleep_5", "label_5"]
data_5=data_5.reset_index(drop=True)

data_6=data_5.drop(data_5.index[0])#though index is always 0, the output for data_6 is began at 6
data_6.columns=["fingerstick_6", "basis_gsr_6", "basis_skintem_6", "acceleration_6", "bolus_6", "basal_6", "meal_6", "basis_sleep_6", "label_6"]
data_6=data_6.reset_index(drop=True)


data_new=pd.concat([data_0,data_1,data_2,data_3,data_4,data_5,data_6],axis=1)
#print(data_new.dropna())
data_new=data_new.dropna()#cut the line that include "NAN"
#print(data_6)
#print(data_new)
#print(data["label"])




new_label=data_6["label_6"]
new_label=new_label.tolist()
#print(len(new_label))
#print(type(new_label))
label_new=new_label[7:]



#change the lbael list into dataframe and combine with the data_new
from pandas.core.frame import DataFrame
n={"label_new": label_new}
data_label=DataFrame(n)
data_complete=pd.concat([data_new,data_label],axis=1)
data_complete=data_complete.dropna()#cut the line that include "NAN"



#balanced the data
x_columns = [x for x in data_complete.columns if x not in ["label_new"]]
X=data_complete[x_columns]
y=data_complete["label_new"]
smote_enn = SMOTEENN(random_state=0)

#why do following redundant thing because SMOTEENN create NaN if I don't do this
X.to_csv("D:\\NCSU Research\\GEARS_Jul9\\GEARS\\540\\avoid_NaN.csv")
filename="D:\\NCSU Research\\GEARS_Jul9\\GEARS\\540\\avoid_NaN.csv"
X_read=pd.read_csv(filename)
X_df=pd.DataFrame(X_read)




X_resampled, y_resampled =smote_enn.fit_resample(X_df,y)
#print(sorted(Counter(y_resampled).items())) #[(-1.0, 5659), (0.0, 3117), (1.0, 3380)]

#check whether the NaN exist again
#nan_list = X_resampled.isnull().sum().tolist()#把每一列的空值个数加起来
#print(nan_list)
#print(sum(nan_list))


#print(X_resampled) #a column with old order exist
X_resampled.drop(labels=["Unnamed: 0"],axis=1,inplace=True)
#print(type(X_resampled)) #dataframe



#standadization
X_scaled=X_resampled.apply(lambda x: (x-np.min(x))/(np.max(x)-np.min(x)))
#can't standadize the label

#Try 2
#X_scale=preprocessing.scale(X_resampled)
#print(X_scale)
#X_scaled=pd.DataFrame(X_scale,columns=x_columns)


#Try3
#colu = [x for x in X_resampled.columns if x not in ["label_new","label","label_1","label_2","label_3","label_4","labe_5","label_6"]]
#print(colu)
#max_min_scaler=lambda x: (x-np.min(x))/(np.max(x)-np.min(x))
#for i in colu:
 #   X_resampled[i] = X_resampled[[i]].apply(max_min_scaler)
#print(X_resampled.mean())

data_f=pd.concat([X_scaled,y_resampled],axis=1)




#print(data_f)
data_f.to_csv("D:\\NCSU Research\\GEARS_Jul9\\GEARS\\540\\data.complete.csv",index=0)
#PermissionError: [Errno 13] Permission denied: 'D:\\NCSU Research\\GEARS_Jul9\\GEARS\\540\\data.complete.csv'


#when building RF, mistake like this: Input contains NaN, infinity or a value too large for dtype('float32')
#nan_list = data_f.isnull().sum().tolist()#把每一列的空值个数加起来
#print(nan_list)
#print(sum(nan_list))