ANTHONY_RUSH_1

import pandas as pd
import string
import numpy as np
import xgboost as xgb
import lightgbm as lgb
from sklearn import svm
from sklearn.neighbors import KNeighborsClassifier
from sklearn.multiclass import OneVsRestClassifier
from sklearn.multiclass import OneVsOneClassifier
from sklearn.svm import LinearSVC
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import RandomForestClassifier
from xgboost import XGBClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder 
from sklearn.decomposition import PCA
from sklearn import metrics   #Additional scklearn functions
from sklearn.model_selection import GridSearchCV
import matplotlib.pylab as plt
from matplotlib.pylab import rcParams
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import confusion_matrix,accuracy_score,plot_confusion_matrix,classification_report,roc_auc_score,f1_score,make_scorer
import seaborn as sns
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
from matplotlib import pyplot
from collections import Counter

from featurewiz import featurewiz

import warnings
warnings.filterwarnings('ignore')

%matplotlib inline

#检查空值
data.isnull().sum().sort_values(ascending=False)

# #字符串转换为数值（整型）
# data['city_level'] = data['city_level'].astype('int')
# #字符串转换为数值（浮点型）
# data['monetary_of_food'] = data['monetary_of_food'].astype('float')
# #更改列名
# #建立字典字典：旧列名和新列名对应关系
# colNameDict = {'InvolceDate':'SaleDate','StockCode':'StockNo'}     

# #!! 一定要旧列名放在冒号前
# #每组对应关系以［逗号］隔开

# data.rename(columns = colNameDict,inplace=True)

#将Y值放到最后
cols=list(data.columns.values)
cols.remove('value_level')
cols.append('value_level')
data=data[cols]
#ID留存
data_keepId=data.iloc[:,0:1]
data=data.drop('md5_buyer_id',axis=1)

# label 从0开始
data[['value_level']]=data[['value_level']]-1

# label encoding
def prepare_targets(X):
    le = LabelEncoder()
    le.fit(X)
    X_enc = le.transform(X)
    return X_enc


data['life_stage']=prepare_targets(data['life_stage'])
data['pre_province']=prepare_targets(data['pre_province'])
#查看label的分布：
labels= data[['value_level']]
sns.countplot(x='value_level',data=labels)
# split into input (X) and output (y) variables
X = data.iloc[:, :-1]
y = data.iloc[:,-1]
scaling=StandardScaler()
scaling.fit(X)
Scaled_X=scaling.transform(X)