andre/100-Days-Of-ML-Code
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update Day 1_Data_Preprocessing.py

Browse Source
This commit is contained in:
yx-xyc
2021-01-14 12:42:31 +08:00
parent 4cd3341120
commit fac63b9c7c
1 changed files with 13 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
Code/Day 1_Data_Preprocessing.py
View File

@ -16,10 +16,11 @@ print(Y)
#Step 3: Handling the missing data #Step 3: Handling the missing data
# If you use the newest version of sklearn, use the lines of code commented out # If you use the newest version of sklearn, use the lines of code commented out
# from sklearn.impute import SimpleImputer from sklearn.impute import SimpleImputer
# imputer = SimpleImputer(missing_values="NaN", strategy="mean") imputer = SimpleImputer(missing_values=np.nan, strategy="mean")
from sklearn.preprocessing import Imputer #from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values = np.nan, strategy = "mean", axis = 0) # axis=0表示按列进行
#imputer = Imputer(missing_values = "NaN", strategy = "mean", axis = 0)
imputer = imputer.fit(X[ : , 1:3]) imputer = imputer.fit(X[ : , 1:3])
X[ : , 1:3] = imputer.transform(X[ : , 1:3]) X[ : , 1:3] = imputer.transform(X[ : , 1:3])
print("---------------------") print("---------------------")
@ -30,11 +31,15 @@ print(X)
#Step 4: Encoding categorical data #Step 4: Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder() from sklearn.compose import ColumnTransformer
X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0]) #labelencoder_X = LabelEncoder()
#X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])
#Creating a dummy variable #Creating a dummy variable
onehotencoder = OneHotEncoder('auto') #print(X)
X = onehotencoder.fit_transform(X).toarray() ct = ColumnTransformer([("", OneHotEncoder(), [0])], remainder = 'passthrough')
X = ct.fit_transform(X)
#onehotencoder = OneHotEncoder(categorical_features = [0])
#X = onehotencoder.fit_transform(X).toarray()
labelencoder_Y = LabelEncoder() labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y) Y = labelencoder_Y.fit_transform(Y)
print("---------------------") print("---------------------")