imputer.fit(housing_num) # In[51]: imputer.statistics_ # Transform the training set: # In[52]: X = imputer.transform(housing_num) X # In[53]: housing_tr = pd.DataFrame(X, columns=housing_num.columns) housing_tr.info() # Now let's preprocess the categorical input feature, `ocean_proximity`: # In[54]:
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# importing the dataset
dataset = pd.read_csv("Data.csv")
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1].values
# Taking care of missing data: Not needed in template
from sklearn.preprocessing import SimpleImputer
missingvalues = SimpleImputer(missing_values=np.nan,
strategy="mean",
verbose=0)
missingvalues = missingvalues.fit(X[:, 1:])
X[:, 1:] = missingvalues.transform(X[:, 1:])
# Encoding Categorical Data: Not needed in template
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
ct = ColumnTransformer([('encoder', OneHotEncoder(), [0])],
remainder='passthrough')
X = np.array(ct.fit_transform(X), dtype=np.float)
from sklearn.preprocessing import LabelEncoder
y = LabelEncoder().fit_transform(y)
# Splitting data
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,
# Data Preprocessing
# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('Data.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 3].values
# Taking care of missing data
from sklearn.preprocessing import SimpleImputer
imputer = SimpleImputer(missing_values='NaN', strategy='mean', axis=0)
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])