# Import libraries necessary for this project
import numpy as np
import pandas as pd
from time import time
from IPython.display import display # Allows the use of display() for DataFrames

# Import supplementary visualization code visuals.py
import visuals as vs

# Pretty display for notebooks
%matplotlib inline

# Load the Census dataset
data = pd.read_csv("census.csv")

# Success - Display the first record
display(data.head(n=1))

# TODO: Total number of records
n_records = len(data)

# Number of records where individual's income is more than $50,000
n_greater_50k = (data['income'] == '>50K').sum()

# Number of records where individual's income is at most $50,000
n_at_most_50k = (data['income'] == '<=50K').sum()

# Percentage of individuals whose income is more than $50,000
greater_percent = (n_greater_50k / n_records) * 100

# Print the results
print("Total number of records: {}".format(n_records))
print("Individuals making more than $50,000: {}".format(n_greater_50k))
print("Individuals making at most $50,000: {}".format(n_at_most_50k))
print("Percentage of individuals making more than $50,000: {}%".format(greater_percent))

Total number of records: 45222
Individuals making more than $50,000: 11208
Individuals making at most $50,000: 34014
Percentage of individuals making more than $50,000: 24.78439697492371%

# Split the data into features and target label
income_raw = data['income']
features_raw = data.drop('income', axis = 1)

# Visualize skewed continuous features of original data
vs.distribution(data)

<Figure size 640x480 with 0 Axes>

# Log-transform the skewed features
skewed = ['capital-gain', 'capital-loss']
features_log_transformed = pd.DataFrame(data = features_raw)
features_log_transformed[skewed] = features_raw[skewed].apply(lambda x: np.log(x + 1))

# Visualize the new log distributions
vs.distribution(features_log_transformed, transformed = True)

<Figure size 640x480 with 0 Axes>

# Import sklearn.preprocessing.StandardScaler
from sklearn.preprocessing import MinMaxScaler

# Initialize a scaler, then apply it to the features
scaler = MinMaxScaler() # default=(0, 1)
numerical = ['age', 'education-num', 'capital-gain', 'capital-loss', 'hours-per-week']

features_log_minmax_transform = pd.DataFrame(data = features_log_transformed)
features_log_minmax_transform[numerical] = scaler.fit_transform(features_log_transformed[numerical])

# Show an example of a record with scaling applied
display(features_log_minmax_transform.head(n = 5))

# One-hot encode the 'features_log_minmax_transform' data using pandas.get_dummies()
features_final = pd.get_dummies(features_log_minmax_transform)

# Encode the 'income_raw' data to numerical values
income_convert = {'<=50K': 0, '>50K': 1}
income = income_raw.map(income_convert)

# Print the number of features after one-hot encoding
encoded = list(features_final.columns)
print("{} total features after one-hot encoding.".format(len(encoded)))

# Uncomment the following line to see the encoded feature names
# print(encoded)

103 total features after one-hot encoding.

# Import train_test_split
from sklearn.model_selection import train_test_split

# Split the 'features' and 'income' data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(features_final, 
                                                    income, 
                                                    test_size = 0.2, 
                                                    random_state = 0)

# Show the results of the split
print("Training set has {} samples.".format(X_train.shape[0]))
print("Testing set has {} samples.".format(X_test.shape[0]))

Training set has 36177 samples.
Testing set has 9045 samples.

# Counting the ones as this is the naive case. 
# Note that 'income' is the 'income_raw' data encoded to numerical values done in the data preprocessing step.
TP = np.sum(income)
FP = income.count() - TP 

TN = 0 # No predicted negatives in the naive case
FN = 0 # No predicted negatives in the naive case

# Calculate accuracy, precision and recall
accuracy = (TP + TN)/(TP + FP + TN + FN )
recall = (TP)/(TP + FN)
precision = (TP)/(TP + FP)

# Calculate F-score using the formula above for beta = 0.5 and correct values for precision and recall.
beta = 0.5
beta_square = beta**2 
fscore = (1 + beta_square)  *(precision*  recall) / ((beta_square * precision) + recall)

# Print the results 
print("Naive Predictor: [Accuracy score: {:.4f}, F-score: {:.4f}]".format(accuracy, fscore))

Naive Predictor: [Accuracy score: 0.2478, F-score: 0.2917]

# Import two metrics from sklearn - fbeta_score and accuracy_score
from sklearn.metrics import fbeta_score, accuracy_score
from time import time

def train_predict(learner, sample_size, X_train, y_train, X_test, y_test): 
    '''
    inputs:
       - learner: the learning algorithm to be trained and predicted on
       - sample_size: the size of samples (number) to be drawn from training set
       - X_train: features training set
       - y_train: income training set
       - X_test: features testing set
       - y_test: income testing set
    '''
    
    results = {}
    
    # Fit the learner to the training data using slicing with 'sample_size' using .fit(training_features[:], training_labels[:])
    start = time() # Get start time
    learner.fit(X_train[:sample_size], y_train[:sample_size])
    end = time() # Get end time
    
    # Calculate the training time
    results['train_time'] = end - start
        
    # Get the predictions on the test set(X_test),
    #       then get predictions on the first 300 training samples(X_train) using .predict()
    start = time() # Get start time
    predictions_test = learner.predict(X_test)
    predictions_train = learner.predict(X_train[:300])
    end = time() # Get end time
    
    # Calculate the total prediction time
    results['pred_time'] = end - start
            
    # Compute accuracy on the first 300 training samples which is y_train[:300]
    results['acc_train'] = accuracy_score(y_train[:300], predictions_train)
        
    # Compute accuracy on test set using accuracy_score()
    results['acc_test'] = accuracy_score(y_test, predictions_test)
    
    # Compute F-score on the the first 300 training samples using fbeta_score()
    results['f_train'] = fbeta_score(y_train[:300], predictions_train, beta=0.5)
        
    # Compute F-score on the test set which is y_test
    results['f_test'] = fbeta_score(y_test, predictions_test, beta=0.5)
       
    # Success
    print("{} trained on {} samples.".format(learner.__class__.__name__, sample_size))
        
    # Return the results
    return results

# Import the three supervised learning models from sklearn
from sklearn.ensemble import AdaBoostClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import SGDClassifier

# Initialize the three models
clf_A = LogisticRegression(random_state=0)  
clf_B = AdaBoostClassifier(algorithm='SAMME', random_state=0)  
clf_C = SGDClassifier(random_state=0)       

# Calculate the number of samples for 1%, 10%, and 100% of the training data
# samples_100 is the entire training set, samples_10 is 10% of samples_100, and samples_1 is 1% of samples_100 

samples_100 = len(y_train)
samples_10 = int(0.1 * samples_100)
samples_1 = int(0.01 * samples_100)

# Collect results on the learners
results = {}
for clf in [clf_A, clf_B, clf_C]:
    clf_name = clf.__class__.__name__
    results[clf_name] = {}
    for i, samples in enumerate([samples_1, samples_10, samples_100]):
        results[clf_name][i] = \
        train_predict(clf, samples, X_train, y_train, X_test, y_test)

# Run metrics visualization for the three supervised learning models chosen
vs.evaluate(results, accuracy, fscore)

LogisticRegression trained on 361 samples.
LogisticRegression trained on 3617 samples.
LogisticRegression trained on 36177 samples.
AdaBoostClassifier trained on 361 samples.
AdaBoostClassifier trained on 3617 samples.
AdaBoostClassifier trained on 36177 samples.
SGDClassifier trained on 361 samples.
SGDClassifier trained on 3617 samples.
SGDClassifier trained on 36177 samples.

<Figure size 640x480 with 0 Axes>

# Import 'GridSearchCV', 'make_scorer', and any other necessary libraries
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import make_scorer, fbeta_score
from sklearn.ensemble import AdaBoostClassifier

# Initialize the classifier
clf = AdaBoostClassifier(algorithm="SAMME", random_state=0)

# Create the parameters list you wish to tune, using a dictionary if needed.
# parameters = {'parameter_1': [value1, value2], 'parameter_2': [value1, value2]}
parameters = {
    'n_estimators': [50, 100, 200], 
    'learning_rate': [0.01, 0.1, 1.0] 
}
# Make an fbeta_score scoring object using make_scorer()
scorer = make_scorer(fbeta_score, beta=0.5)

# Perform grid search on the classifier using 'scorer' as the scoring method using GridSearchCV()
grid_obj = GridSearchCV(estimator=clf, param_grid=parameters, scoring=scorer, cv=3, n_jobs=-1, verbose=1)

# Fit the grid search object to the training data and find the optimal parameters using fit()
grid_fit = grid_obj.fit(X_train, y_train)

# Get the estimator
best_clf = grid_fit.best_estimator_

# Make predictions using the unoptimized and model
predictions = (clf.fit(X_train, y_train)).predict(X_test)
best_predictions = best_clf.predict(X_test)

# Report the before-and-afterscores
print("Unoptimized model\n------")
print("Accuracy score on testing data: {:.4f}".format(accuracy_score(y_test, predictions)))
print("F-score on testing data: {:.4f}".format(fbeta_score(y_test, predictions, beta = 0.5)))
print("\nOptimized Model\n------")
print("Final accuracy score on the testing data: {:.4f}".format(accuracy_score(y_test, best_predictions)))
print("Final F-score on the testing data: {:.4f}".format(fbeta_score(y_test, best_predictions, beta = 0.5)))

Fitting 3 folds for each of 9 candidates, totalling 27 fits
Unoptimized model
------
Accuracy score on testing data: 0.8483
F-score on testing data: 0.7029

Optimized Model
------
Final accuracy score on the testing data: 0.8507
Final F-score on the testing data: 0.7132

# TODO: Import a supervised learning model that has 'feature_importances_'
model = AdaBoostClassifier(algorithm='SAMME', random_state=0)

# TODO: Train the supervised model on the training set using .fit(X_train, y_train)
model = AdaBoostClassifier(random_state=0)
model.fit(X_train, y_train)

# TODO: Extract the feature importances using .feature_importances_ 
importances = model.feature_importances_

# Plot
vs.feature_plot(importances, X_train, y_train)

C:\Users\Janel\anaconda3\Lib\site-packages\sklearn\ensemble\_weight_boosting.py:527: FutureWarning: The SAMME.R algorithm (the default) is deprecated and will be removed in 1.6. Use the SAMME algorithm to circumvent this warning.
  warnings.warn(

<Figure size 640x480 with 0 Axes>

# Import functionality for cloning a model
from sklearn.base import clone

# Reduce the feature space
X_train_reduced = X_train[X_train.columns.values[(np.argsort(importances)[::-1])[:5]]]
X_test_reduced = X_test[X_test.columns.values[(np.argsort(importances)[::-1])[:5]]]

# Train on the "best" model found from grid search earlier
clf = (clone(best_clf)).fit(X_train_reduced, y_train)

# Make new predictions
reduced_predictions = clf.predict(X_test_reduced)

# Report scores from the final model using both versions of data
print("Final Model trained on full data\n------")
print("Accuracy on testing data: {:.4f}".format(accuracy_score(y_test, best_predictions)))
print("F-score on testing data: {:.4f}".format(fbeta_score(y_test, best_predictions, beta = 0.5)))
print("\nFinal Model trained on reduced data\n------")
print("Accuracy on testing data: {:.4f}".format(accuracy_score(y_test, reduced_predictions)))
print("F-score on testing data: {:.4f}".format(fbeta_score(y_test, reduced_predictions, beta = 0.5)))

Final Model trained on full data
------
Accuracy on testing data: 0.8507
F-score on testing data: 0.7132

Final Model trained on reduced data
------
Accuracy on testing data: 0.8263
F-score on testing data: 0.6533

	age	workclass	education_level	education-num	marital-status	occupation	relationship	race	sex	capital-gain	hours-per-week	native-country
0	0.301370	State-gov	Bachelors	0.800000	Never-married	Adm-clerical	Not-in-family	White	Male	0.667492	0.397959	United-States
1	0.452055	Self-emp-not-inc	Bachelors	0.800000	Married-civ-spouse	Exec-managerial	Husband	White	Male	0.000000	0.122449	United-States
2	0.287671	Private	HS-grad	0.533333	Divorced	Handlers-cleaners	Not-in-family	White	Male	0.000000	0.397959	United-States
3	0.493151	Private	11th	0.400000	Married-civ-spouse	Handlers-cleaners	Husband	Black	Male	0.000000	0.397959	United-States
4	0.150685	Private	Bachelors	0.800000	Married-civ-spouse	Prof-specialty	Wife	Black	Female	0.000000	0.397959	Cuba

Machine Learning with PyTorch¶

Project: Finding Donors for CharityML¶

Exploring the Data¶

Implementation: Data Exploration¶

Preparing the Data¶

Transforming Skewed Continuous Features¶

Normalizing Numerical Features¶

Implementation: Data Preprocessing¶

Shuffle and Split Data¶

Evaluating Model Performance¶

Naive Predictor Performance¶

Supervised Learning Models¶

Implementation - Creating a Training and Predicting Pipeline¶

Implementation: Initial Model Evaluation¶

Improving Results¶

Implementation: Model Tuning¶

Final Model Evaluation¶

Results:¶

Feature Relevance Observation¶

Implementation - Extracting Feature Importance¶

Extracting Feature Importance¶

Feature Selection¶

Effects of Feature Selection¶