Supervised Learning with scikit-learn-Preprocessing and pipelines.py

# -*- coding: utf-8 -*-
"""
Created on Tue Jul 23 09:23:59 2019

@author: z
"""
#####################Supervised Learning with scikit-learn-Preprocessing and pipelines
###Exploring categorical features
# Import pandas
import pandas as pd

# Read 'gapminder.csv' into a DataFrame: df
df = pd.read_csv('gapminder.csv')

# Create a boxplot of life expectancy per region
df.boxplot('life', 'Region', rot=60)

# Show the plot
plt.show()



###Creating dummy variables
# Create dummy variables: df_region
df_region = pd.get_dummies(df)

# Print the columns of df_region
print(df_region.columns)

# Create dummy variables with drop_first=True: df_region
df_region = pd.get_dummies(df, drop_first=True)

# Print the new columns of df_region
print(df_region.columns)



###Regression with categorical features
# Import necessary modules
from sklearn.linear_model import Ridge
from sklearn.model_selection import cross_val_score

# Instantiate a ridge regressor: ridge
ridge = Ridge(alpha=0.5, normalize=True)

# Perform 5-fold cross-validation: ridge_cv
ridge_cv = cross_val_score(ridge, X, y, cv=5)

# Print the cross-validated scores
print(ridge_cv)



###Dropping missing data
# Convert '?' to NaN
df[df == '?'] = np.nan

# Print the number of NaNs
print(df.isnull().sum())

# Print shape of original DataFrame
print("Shape of Original DataFrame: {}".format(df.shape))

# Drop missing values and print shape of new DataFrame
df = df.dropna()

# Print shape of new DataFrame
print("Shape of DataFrame After Dropping All Rows with Missing Values: {}".format(df.shape))




###Imputing missing data in a ML Pipeline I
# 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)]




###Imputing missing data in a ML Pipeline II
# 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, random_state=42, test_size=0.3)

# 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))



###Centering and scaling your data
# Import scale
from sklearn.preprocessing import scale

# Scale the features: X_scaled
X_scaled = scale(X)

# Print the mean and standard deviation of the unscaled features
print("Mean of Unscaled Features: {}".format(np.mean(X))) 
print("Standard Deviation of Unscaled Features: {}".format(np.std(X)))

# Print the mean and standard deviation of the scaled features
print("Mean of Scaled Features: {}".format(np.mean(X_scaled))) 
print("Standard Deviation of Scaled Features: {}".format(np.std(X_scaled)))



###Centering and scaling in a pipeline
# Import the necessary modules
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

# Setup the pipeline steps: steps
steps = [('scaler', StandardScaler()),
        ('knn', KNeighborsClassifier())]
        
# Create the pipeline: pipeline
pipeline = Pipeline(steps)

# Create train 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 training set: knn_scaled
knn_scaled = pipeline.fit(X_train, y_train)

# Instantiate and fit a k-NN classifier to the unscaled data
knn_unscaled = KNeighborsClassifier().fit(X_train, y_train)

# Compute and print metrics
print('Accuracy with Scaling: {}'.format(knn_scaled.score(X_test, y_test)))
print('Accuracy without Scaling: {}'.format(knn_unscaled.score(X_test, y_test)))




###Bringing it all together I: 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, random_state=21, test_size=0.2)

# 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_))




###Bringing it all together II: Pipeline for regression