FranciscusRenatus

#Taking care of missing data using Python
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values = 'NaN', strategy = 'mean', axis=0)
imputer = imputer.fit(X[:,1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

FranciscusRenatus

#Taking care of missing data using R
dataset$Age = ifelse(is.na(dataset$Age),
                     ave(dataset$Age, FUN= function(x) mean(x, na.rm = TRUE)),
                     dataset$Age)

dataset$Salary = ifelse(is.na(dataset$Salary),
                     ave(dataset$Salary, FUN= function(x) mean(x, na.rm = TRUE)),
                     dataset$Salary)

FranciscusRenatus

# Encoding categorical data
# Encoding the Independent Variable
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()

#Avoiding dummy variable trap
X = X[:, 1:]

FranciscusRenatus

# Splitting the dataset into train and test set
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

FranciscusRenatus

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train  = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)

FranciscusRenatus

# Fitting Simple Linear Regression to the Training set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)

# Predicting the Test set results
y_pred = regressor.predict(X_test)

FranciscusRenatus

# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder = LabelEncoder()
X[:, 3] = labelencoder.fit_transform(X[:, 3])
onehotencoder = OneHotEncoder(categorical_features = [3])
X = onehotencoder.fit_transform(X).toarray()

# Avoiding the Dummy Variable Trap
X = X[:, 1:]

FranciscusRenatus

# Fitting Multiple Linear Regression to the Training set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)

# Predicting the Test set results
y_pred = regressor.predict(X_test)

FranciscusRenatus

# Visualising the Training set results
plt.scatter(X_train, y_train, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Training set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()

# Visualising the Test set results
plt.scatter(X_test, y_test, color = 'red')

FranciscusRenatus

# Building the optimal model using backward elimination
import statsmodels.formula.api as sm
#Appending the contant as first col of the dataset for readability.
X = np.append(arr = np.ones((50, 1)).astype(int), values = X, axis = 1)
#X_optimized initialized with all features.
X_opt = X[:, [0,1,2,3,4,5]]
#Fitting using OLS
regressor_OLS = sm.OLS(endog = y, exog= X_opt).fit()
#Summary for results, any feature who can be eliminated ?
regressor_OLS.summary()