# coding: utf-8

# In[18]:

import pandas as pd
import numpy as np
from sklearn import tree
from sklearn.svm import SVC
from sklearn.grid_search import GridSearchCV
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.preprocessing import binarize
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import Normalizer
from sklearn.metrics import f1_score
from sklearn.metrics import accuracy_score,recall_score,average_precision_score,auc

# In[32]:

data=pd.read_csv(r"D:\Users\sgg91044\Desktop\bad_wafer_data_pivot.csv")

# In[33]:

data.head()

# In[34]:

index=data.drop(columns=["defect_count","ETCM_PHA4","ETCM_PHB4","ETCM_PHC4","HELK_MAX.","HELK_MEAN","HELK_SD","LOWERCHM_PRESS","PBK4","RR13_MAX.","RR13_MEAN","RR23_MAX.","RR23_MEAN","THR3_MAX.","THR3_MAX._DIFF","THR3_MEAN","THR3_MEAN_DIFF","THR3_MEAN_SLOPE","THR3_SD"])
index=index.drop(columns="Target")
index

# In[35]:

data=data.drop(columns=["lotid","Step","Recipie_Name","defect_count"])
data.head()

# In[36]:

ohe = OneHotEncoder()
le = LabelEncoder()

# In[37]:

data.head()

# In[40]:

data["eqp_encoded"] = le.fit_transform(data.iloc[:,0])
data["slot_encoded"] = le.fit_transform(data.iloc[:,1])
data[‘chamber_encoded‘] = le.fit_transform(data.iloc[:,2])
data.head()

# In[41]:

data=data.drop(columns=["eqpid","slotid","Chamber"])
data.head()

# In[42]:

nz = Normalizer()
data.iloc[:,10:12]=pd.DataFrame(nz.fit_transform(data.iloc[:,10:12]),columns=data.iloc[:,10:12].columns)
data.iloc[:,0:3]=pd.DataFrame(nz.fit_transform(data.iloc[:,0:3]),columns=data.iloc[:,0:3].columns)
data.head()

# In[43]:

def cleaning():
data=pd.read_csv(r"D:\Users\sgg91044\Desktop\bad_wafer_data_pivot.csv")
data=data.drop(columns=["lotid","Step","Recipie_Name","defect_count"])
le = LabelEncoder()
data["eqp_encoded"] = le.fit_transform(data.iloc[:,0])
data["slot_encoded"] = le.fit_transform(data.iloc[:,1])
data[‘chamber_encoded‘] = le.fit_transform(data.iloc[:,2])
data=data.drop(columns=["eqpid","slotid","Chamber"])
nz = Normalizer()
data.iloc[:,10:12]=pd.DataFrame(nz.fit_transform(data.iloc[:,10:12]),columns=data.iloc[:,10:12].columns)
data.iloc[:,0:3]=pd.DataFrame(nz.fit_transform(data.iloc[:,0:3]),columns=data.iloc[:,0:3].columns)

我的代碼-cleaning