Preprocessing

Pipeline and Imputer

In a pipeline, each step but the last one must be a transformer. The last must be an estimater like a regressor, a classifier.

# Import the Imputer module
from sklearn.preprocessing import Imputer
from sklearn.svm import SVC

# Setup the Imputation transformer: imp
imp = Imputer(missing_values='NaN', strategy='most_frequent', axis=0)

# Instantiate the SVC classifier: clf
clf = SVC()

# Setup the pipeline with the required steps: steps
steps = [('imputation', imp),
        ('SVM', clf)]

Example 2:

# Import necessary modules
from sklearn.preprocessing import Imputer
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC

# Setup the pipeline steps: steps
steps = [('imputation', Imputer(missing_values='NaN', strategy='most_frequent', axis=0)),
        ('SVM', SVC())]

# Create the pipeline: pipeline
pipeline = Pipeline(steps)

# Create training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Fit the pipeline to the train set
pipeline.fit(X_train, y_train)

# Predict the labels of the test set
y_pred = pipeline.predict(X_test)

# Compute metrics
print(classification_report(y_test, y_pred))

Normalizing and standardizing

Standardizing: Subtract the mean and divide by the variance.

Also you could subtract the minimum and divide by the range : Min 0 and Max 1.

Pipeline for classification

# Setup the pipeline
steps = [('scaler', StandardScaler()),
         ('SVM', SVC())]

pipeline = Pipeline(steps)

# Specify the hyperparameter space
parameters = {'SVM__C':[1, 10, 100],
              'SVM__gamma':[0.1, 0.01]}

# Create train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state= 21)

# Instantiate the GridSearchCV object: cv
cv = GridSearchCV(pipeline, parameters, cv = 3)

# Fit to the training set
cv.fit(X_train, y_train)

# Predict the labels of the test set: y_pred
y_pred = cv.predict(X_test)

# Compute and print metrics
print("Accuracy: {}".format(cv.score(X_test, y_test)))
print(classification_report(y_test, y_pred))
print("Tuned Model Parameters: {}".format(cv.best_params_))

Pipeline for regression

# Setup the pipeline steps: steps
steps = [('imputation', Imputer(missing_values='NaN', strategy='mean', axis=0)),
         ('scaler', StandardScaler()),
         ('elasticnet', ElasticNet())]

# Create the pipeline: pipeline 
pipeline = Pipeline(steps)

# Specify the hyperparameter space
parameters = {'elasticnet__l1_ratio':np.linspace(0,1,30)}

# Create train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=42)

# Create the GridSearchCV object: gm_cv
gm_cv = GridSearchCV(pipeline, parameters, cv = 3)

# Fit to the training set
gm_cv.fit(X_train, y_train)

# Compute and print the metrics
r2 = gm_cv.score(X_test, y_test)
print("Tuned ElasticNet Alpha: {}".format(gm_cv.best_params_))
print("Tuned ElasticNet R squared: {}".format(r2))