Supervised Learning with scikit-learn

#Linear Regression 1

# Import LinearRegression
from sklearn.linear_model import LinearRegression

# Create the regressor: reg
reg = LinearRegression()

# Create the prediction space
prediction_space = np.linspace(min(X_fertility), max(X_fertility)).reshape(-1,1)

# Fit the model to the data
reg.fit(X_fertility, y)

# Compute predictions over the prediction space: y_pred
y_pred = reg.predict(prediction_space)

# Print R^2 
print(reg.score(X_fertility, y))

# Plot regression line
plt.plot(prediction_space, y_pred, color='black', linewidth=3)
plt.show()

# Linear Regression 2

# Import necessary modules
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split

# 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)

# Create the regressor: reg_all
reg_all = LinearRegression()

# Fit the regressor to the training data
reg_all.fit(X_train, y_train)

# Predict on the test data: y_pred
y_pred = reg_all.predict(X_test)

# Compute and print R^2 and RMSE
print("R^2: {}".format(reg_all.score(X_test, y_test)))
rmse = np.sqrt(mean_squared_error(y_test, y_pred))
print("Root Mean Squared Error: {}".format(rmse))


# CV Score

# 5-fold

# Import the necessary modules
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LinearRegression

# Create a linear regression object: reg
reg = LinearRegression()

# Compute 5-fold cross-validation scores: cv_scores
cv_scores = cross_val_score(reg, X, y, cv=5)

# Print the 5-fold cross-validation scores
print(cv_scores)

print("Average 5-Fold CV Score: {}".format(np.mean(cv_scores)))

# 3-fold CV and 10-fold CV

# Import necessary modules
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import cross_val_score

# Create a linear regression object: reg
reg = LinearRegression()

# Perform 3-fold CV
cvscores_3 = cross_val_score(reg, X, y, cv=3)
print(np.mean(cvscores_3))

# Perform 10-fold CV
cvscores_10 = cross_val_score(reg, X, y, cv=10)
print(np.mean(cvscores_10))

# Lasso with an alpha of 0.4

# Import Lasso
from sklearn.linear_model import Lasso

# Instantiate a lasso regressor: lasso
lasso = Lasso(alpha=0.4, normalize=True)

# Fit the regressor to the data
lasso.fit(X, y)

# Compute and print the coefficients
lasso_coef = lasso.fit(X,y).coef_
print(lasso_coef)

# Plot the coefficients
plt.plot(range(len(df_columns)), lasso_coef)
plt.xticks(range(len(df_columns)), df_columns.values, rotation=60)
plt.margins(0.02)
plt.show()


# Ridge regularizer

# Import necessary modules
from sklearn.linear_model import Ridge
from sklearn.model_selection import cross_val_score

# Setup the array of alphas and lists to store scores
alpha_space = np.logspace(-4, 0, 50)
ridge_scores = []
ridge_scores_std = []

# Create a ridge regressor: ridge
ridge = Ridge(normalize=True)

# Compute scores over range of alphas
for alpha in alpha_space:

    # Specify the alpha value to use: ridge.alpha
    ridge.alpha = alpha
    
    # Perform 10-fold CV: ridge_cv_scores
    ridge_cv_scores = cross_val_score(ridge, X, y, cv=10)
    
    # Append the mean of ridge_cv_scores to ridge_scores
    ridge_scores.append(np.mean(ridge_cv_scores))
    
    # Append the std of ridge_cv_scores to ridge_scores_std
    ridge_scores_std.append(np.std(ridge_cv_scores))

# Display the plot
display_plot(ridge_scores, ridge_scores_std)

# Model Evaluation

# Import necessary modules
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report

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

# Instantiate a k-NN classifier: knn
knn = KNeighborsClassifier(n_neighbors=6)

# Fit the classifier to the training data
knn.fit(X_train, y_train)

# Predict the labels of the test data: y_pred
y_pred = knn.predict(X_test)

# Generate the confusion matrix and classification report
print(confusion_matrix(y_test, y_pred))
print(classification_report(y_test, y_pred))

# Logistic Regression

# Import the necessary modules
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix, classification_report

# Create training 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 classifier: logreg
logreg = LogisticRegression()

# Fit the classifier to the training data
logreg.fit(X_train, y_train)

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

# Compute and print the confusion matrix and classification report
print(confusion_matrix(y_test, y_pred))
print(classification_report(y_test, y_pred))

# Computing receiver operating characterisitic curve

# Import necessary modules
from sklearn.metrics import roc_curve

# Compute predicted probabilities: y_pred_prob
y_pred_prob = logreg.predict_proba(X_test)[:,1]

# Generate ROC curve values: fpr, tpr, thresholds
fpr, tpr, thresholds = roc_curve(y_test, y_pred_prob)

# Plot ROC curve
plt.plot([0, 1], [0, 1], 'k--')
plt.plot(fpr, tpr)
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC Curve')
plt.show()

# Hyperparameter tuning

# Import necessary modules
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV

# Setup the hyperparameter grid
c_space = np.logspace(-5, 8, 15)
param_grid = {'C': c_space}

# Instantiate a logistic regression classifier: logreg
logreg = LogisticRegression()

# Instantiate the GridSearchCV object: logreg_cv
logreg_cv = GridSearchCV(logreg, param_grid, cv=5)

# Fit it to the data
logreg_cv.fit(X, y)

# Print the tuned parameters and score
print("Tuned Logistic Regression Parameters: {}".format(logreg_cv.best_params_)) 
print("Best score is {}".format(logreg_cv.best_score_))
 
# HPT with RandomizedSearchCV

# Import necessary modules
from scipy.stats import randint
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import RandomizedSearchCV

# Setup the parameters and distributions to sample from: param_dist
param_dist = {"max_depth": [3, None],
              "max_features": randint(1, 9),
              "min_samples_leaf": randint(1, 9),
              "criterion": ["gini", "entropy"]}

# Instantiate a Decision Tree classifier: tree
tree = DecisionTreeClassifier()

# Instantiate the RandomizedSearchCV object: tree_cv
tree_cv = RandomizedSearchCV(tree, param_dist, cv=5)

# Fit it to the data
tree_cv.fit(X, y)

# Print the tuned parameters and score
print("Tuned Decision Tree Parameters: {}".format(tree_cv.best_params_))
print("Best score is {}".format(tree_cv.best_score_))

# Hold-out set practice part 1

# Import necessary modules
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV

# Create the hyperparameter grid
c_space = np.logspace(-5, 8, 15)
param_grid = {'C': c_space, 'penalty': ['l1', 'l2']}

# Instantiate the logistic regression classifier: logreg
logreg = LogisticRegression()

# 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)

# Instantiate the GridSearchCV object: logreg_cv
logreg_cv = GridSearchCV(logreg, param_grid, cv=5)

# Fit it to the training data
logreg_cv.fit(X_train, y_train)

# Print the optimal parameters and best score
print("Tuned Logistic Regression Parameter: {}".format(logreg_cv.best_params_))
print("Tuned Logistic Regression Accuracy: {}".format(logreg_cv.best_score_))

# Regression with categorical variables

# 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)

# Imputing Missing Data In a ML Pipeline

# 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, 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))


# Centering and Scaling 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, test_size=0.2, random_state=21)

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

# 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, param_grid=parameters)

# 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))