Udacity ML - Finding Donors for CharityML

This is a project submission for the Udacity Machine Learning Engineer Nanodegree programme. I’ve removed submission information sections that are not relevant. For this tutorial I was using Python 2.7.

In the code, sections labeled # ToDo: are where code has been added.

Getting Started

In this project, you will employ several supervised algorithms of your choice to accurately model individuals’ income using data collected from the 1994 U.S. Census. You will then choose the best candidate algorithm from preliminary results and further optimize this algorithm to best model the data. Your goal with this implementation is to construct a model that accurately predicts whether an individual makes more than $50,000. This sort of task can arise in a non-profit setting, where organizations survive on donations. Understanding an individual’s income can help a non-profit better understand how large of a donation to request, or whether or not they should reach out to begin with. While it can be difficult to determine an individual’s general income bracket directly from public sources, we can (as we will see) infer this value from other publically available features.

The dataset for this project originates from the UCI Machine Learning Repository. The datset was donated by Ron Kohavi and Barry Becker, after being published in the article “Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid”. You can find the article by Ron Kohavi online. The data we investigate here consists of small changes to the original dataset, such as removing the 'fnlwgt' feature and records with missing or ill-formatted entries.

---

Exploring the Data

Run the code cell below to load necessary Python libraries and load the census data. Note that the last column from this dataset, 'income', will be our target label (whether an individual makes more than, or at most, $50,000 annually). All other columns are features about each individual in the census database.

# 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))

Implementation: Data Exploration

A cursory investigation of the dataset will determine how many individuals fit into either group, and will tell us about the percentage of these individuals making more than \$50,000. In the code cell below, you will need to compute the following: - The total number of records, 'n_records' - The number of individuals making more than \$50,000 annually, 'n_greater_50k'. - The number of individuals making at most \$50,000 annually, 'n_at_most_50k'. - The percentage of individuals making more than \$50,000 annually, 'greater_percent'.

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

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

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

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

# 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: {:.2f}%".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: 24.78%

Featureset Exploration

• age: continuous.
• workclass: Private, Self-emp-not-inc, Self-emp-inc, Federal-gov, Local-gov, State-gov, Without-pay, Never-worked.
• education: Bachelors, Some-college, 11th, HS-grad, Prof-school, Assoc-acdm, Assoc-voc, 9th, 7th-8th, 12th, Masters, 1st-4th, 10th, Doctorate, 5th-6th, Preschool.
• education-num: continuous.
• marital-status: Married-civ-spouse, Divorced, Never-married, Separated, Widowed, Married-spouse-absent, Married-AF-spouse.
• occupation: Tech-support, Craft-repair, Other-service, Sales, Exec-managerial, Prof-specialty, Handlers-cleaners, Machine-op-inspct, Adm-clerical, Farming-fishing, Transport-moving, Priv-house-serv, Protective-serv, Armed-Forces.
• relationship: Wife, Own-child, Husband, Not-in-family, Other-relative, Unmarried.
• race: Black, White, Asian-Pac-Islander, Amer-Indian-Eskimo, Other.
• sex: Female, Male.
• capital-gain: continuous.
• capital-loss: continuous.
• hours-per-week: continuous.
• native-country: United-States, Cambodia, England, Puerto-Rico, Canada, Germany, Outlying-US(Guam-USVI-etc), India, Japan, Greece, South, China, Cuba, Iran, Honduras, Philippines, Italy, Poland, Jamaica, Vietnam, Mexico, Portugal, Ireland, France, Dominican-Republic, Laos, Ecuador, Taiwan, Haiti, Columbia, Hungary, Guatemala, Nicaragua, Scotland, Thailand, Yugoslavia, El-Salvador, Trinadad&Tobago, Peru, Hong, Holand-Netherlands.

---

Preparing the Data

Before data can be used as input for machine learning algorithms, it often must be cleaned, formatted, and restructured — this is typically known as preprocessing. Fortunately, for this dataset, there are no invalid or missing entries we must deal with, however, there are some qualities about certain features that must be adjusted. This preprocessing can help tremendously with the outcome and predictive power of nearly all learning algorithms.

Transforming Skewed Continuous Features

A dataset may sometimes contain at least one feature whose values tend to lie near a single number, but will also have a non-trivial number of vastly larger or smaller values than that single number. Algorithms can be sensitive to such distributions of values and can underperform if the range is not properly normalized. With the census dataset two features fit this description: ‘capital-gain' and 'capital-loss'.

Run the code cell below to plot a histogram of these two features. Note the range of the values present and how they are distributed.

# 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)

For highly-skewed feature distributions such as 'capital-gain' and 'capital-loss', it is common practice to apply a logarithmic transformation on the data so that the very large and very small values do not negatively affect the performance of a learning algorithm. Using a logarithmic transformation significantly reduces the range of values caused by outliers. Care must be taken when applying this transformation however: The logarithm of 0 is undefined, so we must translate the values by a small amount above 0 to apply the the logarithm successfully.

Run the code cell below to perform a transformation on the data and visualize the results. Again, note the range of values and how they are distributed.

# 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)

Normalizing Numerical Features

In addition to performing transformations on features that are highly skewed, it is often good practice to perform some type of scaling on numerical features. Applying a scaling to the data does not change the shape of each feature’s distribution (such as 'capital-gain' or 'capital-loss' above); however, normalization ensures that each feature is treated equally when applying supervised learners. Note that once scaling is applied, observing the data in its raw form will no longer have the same original meaning, as exampled below.

Run the code cell below to normalize each numerical feature. We will use sklearn.preprocessing.MinMaxScaler for this.

# 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))

Implementation: Data Preprocessing

From the table in Exploring the Data above, we can see there are several features for each record that are non-numeric. Typically, learning algorithms expect input to be numeric, which requires that non-numeric features (called categorical variables) be converted. One popular way to convert categorical variables is by using the one-hot encoding scheme. One-hot encoding creates a “dummy” variable for each possible category of each non-numeric feature. For example, assume someFeature has three possible entries: A, B, or C. We then encode this feature into someFeature_A, someFeature_B and someFeature_C.

Additionally, as with the non-numeric features, we need to convert the non-numeric target label, 'income' to numerical values for the learning algorithm to work. Since there are only two possible categories for this label (”<=50K” and “>50K”), we can avoid using one-hot encoding and simply encode these two categories as 0 and 1, respectively. In code cell below, you will need to implement the following: - Use pandas.get_dummies() to perform one-hot encoding on the 'features_raw' data. - Convert the target label 'income_raw' to numerical entries. - Set records with “<=50K” to 0 and records with “>50K” to 1.

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

# TODO: Encode the 'income_raw' data to numerical values
income = pd.get_dummies(income_raw)['>50K']

# 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.
['age', 'education-num', 'capital-gain', 'capital-loss', 'hours-per-week', 'workclass_ Federal-gov', 'workclass_ Local-gov', 'workclass_ Private', 'workclass_ Self-emp-inc', 'workclass_ Self-emp-not-inc', 'workclass_ State-gov', 'workclass_ Without-pay', 'education_level_ 10th', 'education_level_ 11th', 'education_level_ 12th', 'education_level_ 1st-4th', 'education_level_ 5th-6th', 'education_level_ 7th-8th', 'education_level_ 9th', 'education_level_ Assoc-acdm', 'education_level_ Assoc-voc', 'education_level_ Bachelors', 'education_level_ Doctorate', 'education_level_ HS-grad', 'education_level_ Masters', 'education_level_ Preschool', 'education_level_ Prof-school', 'education_level_ Some-college', 'marital-status_ Divorced', 'marital-status_ Married-AF-spouse', 'marital-status_ Married-civ-spouse', 'marital-status_ Married-spouse-absent', 'marital-status_ Never-married', 'marital-status_ Separated', 'marital-status_ Widowed', 'occupation_ Adm-clerical', 'occupation_ Armed-Forces', 'occupation_ Craft-repair', 'occupation_ Exec-managerial', 'occupation_ Farming-fishing', 'occupation_ Handlers-cleaners', 'occupation_ Machine-op-inspct', 'occupation_ Other-service', 'occupation_ Priv-house-serv', 'occupation_ Prof-specialty', 'occupation_ Protective-serv', 'occupation_ Sales', 'occupation_ Tech-support', 'occupation_ Transport-moving', 'relationship_ Husband', 'relationship_ Not-in-family', 'relationship_ Other-relative', 'relationship_ Own-child', 'relationship_ Unmarried', 'relationship_ Wife', 'race_ Amer-Indian-Eskimo', 'race_ Asian-Pac-Islander', 'race_ Black', 'race_ Other', 'race_ White', 'sex_ Female', 'sex_ Male', 'native-country_ Cambodia', 'native-country_ Canada', 'native-country_ China', 'native-country_ Columbia', 'native-country_ Cuba', 'native-country_ Dominican-Republic', 'native-country_ Ecuador', 'native-country_ El-Salvador', 'native-country_ England', 'native-country_ France', 'native-country_ Germany', 'native-country_ Greece', 'native-country_ Guatemala', 'native-country_ Haiti', 'native-country_ Holand-Netherlands', 'native-country_ Honduras', 'native-country_ Hong', 'native-country_ Hungary', 'native-country_ India', 'native-country_ Iran', 'native-country_ Ireland', 'native-country_ Italy', 'native-country_ Jamaica', 'native-country_ Japan', 'native-country_ Laos', 'native-country_ Mexico', 'native-country_ Nicaragua', 'native-country_ Outlying-US(Guam-USVI-etc)', 'native-country_ Peru', 'native-country_ Philippines', 'native-country_ Poland', 'native-country_ Portugal', 'native-country_ Puerto-Rico', 'native-country_ Scotland', 'native-country_ South', 'native-country_ Taiwan', 'native-country_ Thailand', 'native-country_ Trinadad&Tobago', 'native-country_ United-States', 'native-country_ Vietnam', 'native-country_ Yugoslavia']

Shuffle and Split Data

Now all categorical variables have been converted into numerical features, and all numerical features have been normalized. As always, we will now split the data (both features and their labels) into training and test sets. 80% of the data will be used for training and 20% for testing.

Run the code cell below to perform this split.

# Import train_test_split
from sklearn.cross_validation 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.

---

Evaluating Model Performance

In this section, we will investigate four different algorithms, and determine which is best at modeling the data. Three of these algorithms will be supervised learners of your choice, and the fourth algorithm is known as a naive predictor.

Metrics and the Naive Predictor

CharityML, equipped with their research, knows individuals that make more than \$50,000 are most likely to donate to their charity. Because of this, CharityML is particularly interested in predicting who makes more than \$50,000 accurately. It would seem that using accuracy as a metric for evaluating a particular model’s performace would be appropriate. Additionally, identifying someone that does not make more than \$50,000 as someone who does would be detrimental to CharityML, since they are looking to find individuals willing to donate. Therefore, a model’s ability to precisely predict those that make more than \$50,000 is more important than the model’s ability to recall those individuals. We can use F-beta score as a metric that considers both precision and recall:

$$ F_{\beta} = (1 + \beta^2) \cdot \frac{precision \cdot recall}{\left( \beta^2 \cdot precision \right) + recall} $$

In particular, when $\beta = 0.5$, more emphasis is placed on precision. This is called the F$_{0.5}$ score (or F-score for simplicity).

Looking at the distribution of classes (those who make at most \$50,000, and those who make more), it’s clear most individuals do not make more than \$50,000. This can greatly affect accuracy, since we could simply say “this person does not make more than \$50,000” and generally be right, without ever looking at the data! Making such a statement would be called naive, since we have not considered any information to substantiate the claim. It is always important to consider the naive prediction for your data, to help establish a benchmark for whether a model is performing well. That been said, using that prediction would be pointless: If we predicted all people made less than \$50,000, CharityML would identify no one as donors.

Note: Recap of accuracy, precision, recall

Accuracy measures how often the classifier makes the correct prediction. It’s the ratio of the number of correct predictions to the total number of predictions (the number of test data points).

Precision tells us what proportion of messages we classified as spam, actually were spam. It is a ratio of true positives(words classified as spam, and which are actually spam) to all positives(all words classified as spam, irrespective of whether that was the correct classificatio), in other words it is the ratio of

[True Positives/(True Positives + False Positives)]

Recall(sensitivity) tells us what proportion of messages that actually were spam were classified by us as spam. It is a ratio of true positives(words classified as spam, and which are actually spam) to all the words that were actually spam, in other words it is the ratio of

[True Positives/(True Positives + False Negatives)]

For classification problems that are skewed in their classification distributions like in our case, for example if we had a 100 text messages and only 2 were spam and the rest 98 weren’t, accuracy by itself is not a very good metric. We could classify 90 messages as not spam(including the 2 that were spam but we classify them as not spam, hence they would be false negatives) and 10 as spam(all 10 false positives) and still get a reasonably good accuracy score. For such cases, precision and recall come in very handy. These two metrics can be combined to get the F1 score, which is weighted average(harmonic mean) of the precision and recall scores. This score can range from 0 to 1, with 1 being the best possible F1 score(we take the harmonic mean as we are dealing with ratios).

Question 1 - Naive Predictor Performace

• If we chose a model that always predicted an individual made more than $50,000, what would that model’s accuracy and F-score be on this dataset? You must use the code cell below and assign your results to 'accuracy' and 'fscore' to be used later.

• When we have a model that always predicts ‘1’ (i.e. the individual makes more than 50k) then our model will have no True Negatives(TN) or False Negatives(FN) as we are not making any negative(‘0’ value) predictions. Therefore our Accuracy in this case becomes the same as our Precision(True Positives/(True Positives + False Positives)) as every prediction that we have made with value ‘1’ that should have ‘0’ becomes a False Positive; therefore our denominator in this case is the total number of records we have in total.

• Our Recall score(True Positives/(True Positives + False Negatives)) in this setting becomes 1 as we have no False Negatives.

# 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 # Specific to the naive case

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

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

# TODO: Calculate F-score using the formula above for beta = 0.5 and correct values for precision and recall.
# HINT: The formula above can be written as (1 + beta**2) * (precision * recall) / ((beta**2 * precision) + recall)
beta = 0.5
fscore = (1 + beta**2) * (precision * recall) / ((beta**2 * 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]

Supervised Learning Models

The following are some of the supervised learning models that are currently available in scikit-learn that you may choose from: - Gaussian Naive Bayes (GaussianNB) - Decision Trees - Ensemble Methods (Bagging, AdaBoost, Random Forest, Gradient Boosting) - K-Nearest Neighbors (KNeighbors) - Stochastic Gradient Descent Classifier (SGDC) - Support Vector Machines (SVM) - Logistic Regression

Question 2 - Model Application

List three of the supervised learning models above that are appropriate for this problem that you will test on the census data. For each model chosen

• Describe one real-world application in industry where the model can be applied.
• What are the strengths of the model; when does it perform well?
• What are the weaknesses of the model; when does it perform poorly?
• What makes this model a good candidate for the problem, given what you know about the data?

Structure your answer in the same format as above^, with 4 parts for each of the three models you pick. Please include references with your answer.

Answer:

1: Logistic Regression

• Understanding the factors behind success/failure in a university examination e.g. age, race, gender, attendance etc. https://www.craftonhills.edu/~/media/Files/SBCCD/CHC/About%20CHC/Research%20and%20Planning/Presentations/Using_Logistic_Regression.pdf
• Logistic regression is good at predicting a probability of success given independent attributes. It is quick to run as it has a numerical solution. It’s not a black box solution and provides sensible outputs and significance tests that show you the impact of each variable.
• Continuous loss function can mean that it’s sensitive to outliers e.g. in cases where there are only a few positive results, it will likely overfit unless additional penalties are used.
• We have a binary output, with a high quantity of positive responses. Logistic regression is simple and quick to use as a benchmark model

2: Gradient Boosting

• Predicting the patterns of mobility for people in a city based on factors like time of day, modes of transport etc. https://pdfs.semanticscholar.org/b2ad/d0895090152a5aea893e1f1421e6fb905ea3.pdf
• It’s good for modelling complex data sets that could have both linear and non-linear variables, and hard to quantify interactions between them. It’s flexible as it can be used for classification and regression. It’s fairly quick and also can extract feature importance and graphical relationships.
• Weakness is that it can be time consuming to train the model well as there are a large number of hyperparameters to train e.g. the learning rate, the tree depth, regularisation parameters. It can overfit easily if not trained properly e.g. too many trees and no regularisation. As its creating decision trees, the boundary space isn’t smooth, so can give unnatural results that will be worse if a simple numerical solution exists e.g. a simple linear boundary.
• We have a lot of features: 103, which can make it a challenge to work with. Gradient Boosting will naturally find the most important features, and can provide insights about how the decision boundaries look like. It’s rich with features to test to try and get the best result.

3: K-nearest neighbours

• Classification of heart disease with KNN: https://arxiv.org/ftp/arxiv/papers/1508/1508.02061.pdf
• It is easy to train a new observation, as its instance based, it’s easy to use and the results are interpretable.
• It’s a lazy learner, which makes it slow at predicting. As it doesn’t store a model, it has to run the algorithm every time a new observation is available to predict. This would be slow in a prediction engine for real time data. Not robust to noisy data.
• We are more concerned with having a high confidence that when we predict a person to be over >50k, it is correct. Thought maybe KNN with a high K, may predict this occurance less frequently but with more accuracy in cases where there are clear clusters.

Implementation - Creating a Training and Predicting Pipeline

To properly evaluate the performance of each model you’ve chosen, it’s important that you create a training and predicting pipeline that allows you to quickly and effectively train models using various sizes of training data and perform predictions on the testing data. Your implementation here will be used in the following section. In the code block below, you will need to implement the following: - Import fbeta_score and accuracy_score from sklearn.metrics. - Fit the learner to the sampled training data and record the training time. - Perform predictions on the test data X_test, and also on the first 300 training points X_train[:300]. - Record the total prediction time. - Calculate the accuracy score for both the training subset and testing set. - Calculate the F-score for both the training subset and testing set. - Make sure that you set the beta parameter!

from sklearn.metrics import fbeta_score
from sklearn.metrics import accuracy_score

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 = {}
    
    # TODO: Fit the learner to the training data using slicing with 'sample_size' using .fit(training_features[:], training_labels[:])
    start = time() # Get start time
    learner = learner.fit(X_train[0:sample_size], y_train[0:sample_size])
    end = time() # Get end time
    
    # TODO: Calculate the training time
    results['train_time'] = end - start
        
    # TODO: 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[0:300])
    end = time() # Get end time
    
    # TODO: Calculate the total prediction time
    results['pred_time'] = end - start
            
    # TODO: Compute accuracy on the first 300 training samples which is y_train[:300]
    results['acc_train'] = accuracy_score(y_train[0:300], predictions_train)
        
    # TODO: Compute accuracy on test set using accuracy_score()
    results['acc_test'] = accuracy_score(y_test, predictions_test)
    
    # TODO: Compute F-score on the the first 300 training samples using fbeta_score()
    beta = 0.5
    results['f_train'] = fbeta_score(y_train[0:300], predictions_train, beta = beta)
        
    # TODO: Compute F-score on the test set which is y_test
    results['f_test'] = fbeta_score(y_test, predictions_test, beta = beta)
       
    # Success
    print "{} trained on {} samples.".format(learner.__class__.__name__, sample_size)
        
    # Return the results
    return results

Implementation: Initial Model Evaluation

In the code cell, you will need to implement the following: - Import the three supervised learning models you’ve discussed in the previous section. - Initialize the three models and store them in 'clf_A', 'clf_B', and 'clf_C'. - Use a 'random_state' for each model you use, if provided. - Note: Use the default settings for each model — you will tune one specific model in a later section. - Calculate the number of records equal to 1%, 10%, and 100% of the training data. - Store those values in 'samples_1', 'samples_10', and 'samples_100' respectively.

Note: Depending on which algorithms you chose, the following implementation may take some time to run!

# TODO: Import the three supervised learning models from sklearn
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.neighbors import KNeighborsClassifier

# others for testing
from sklearn.svm import SVC
from sklearn.linear_model import SGDClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier

# TODO: Initialize the three models
clf_A = LogisticRegression()
clf_B = GradientBoostingClassifier()
clf_C = KNeighborsClassifier()


# TODO: Calculate the number of samples for 1%, 10%, and 100% of the training data
# HINT: samples_100 is the entire training set i.e. len(y_train)
# HINT: samples_10 is 10% of samples_100
# HINT: samples_1 is 1% of samples_100
samples_100 = len(y_train)
samples_10 = int(samples_100 * 0.1)
samples_1 = int(samples_100 * 0.01)

# 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.
GradientBoostingClassifier trained on 361 samples.
GradientBoostingClassifier trained on 3617 samples.
GradientBoostingClassifier trained on 36177 samples.
KNeighborsClassifier trained on 361 samples.
KNeighborsClassifier trained on 3617 samples.
KNeighborsClassifier trained on 36177 samples.

---

Improving Results

In this final section, you will choose from the three supervised learning models the best model to use on the student data. You will then perform a grid search optimization for the model over the entire training set (X_train and y_train) by tuning at least one parameter to improve upon the untuned model’s F-score.

Question 3 - Choosing the Best Model

• Based on the evaluation you performed earlier, in one to two paragraphs, explain to CharityML which of the three models you believe to be most appropriate for the task of identifying individuals that make more than \$50,000.

Look at the graph at the bottom left from the cell above(the visualization created by vs.evaluate(results, accuracy, fscore)) and check the F score for the testing set when 100% of the training set is used. Which model has the highest score? Your answer should include discussion of the: * metrics - F score on the testing when 100% of the training data is used, * prediction/training time * the algorithm’s suitability for the data.

Answer:

I will select Gradient Boosting out of the three models - It’s produced the highest F-score for all sizes of sampled data, in both the test and training sets. This is the out of the box solution too. One would expect that this can be improved with some hyperparameter tuning - Logistic regression is quicker, but not significantly so. Gradient Boosting has taken 8 seconds which is fine with this amount of data. KNN is the slowest and produces the worst F-scores - Gradient boosting is suitable for classification problems like these and does have feature importance capabilities. The results would suggest it’s suitable too

Question 4 - Describing the Model in Layman’s Terms

• In one to two paragraphs, explain to CharityML, in layman’s terms, how the final model chosen is supposed to work. Be sure that you are describing the major qualities of the model, such as how the model is trained and how the model makes a prediction. Avoid using advanced mathematical jargon, such as describing equations.

When explaining your model, if using external resources please include all citations.

Answer:

Good source: https://machinelearningmastery.com/gentle-introduction-gradient-boosting-algorithm-machine-learning/

Summary:

Gradient Boosting starts by picking a simple, but ill informed solution to the problem. It will then try to improve this solution in steps, until its built a model. For instance in this case the first solution may be that all people have higher than 50K wage. It will then check how well it has done and compute a residual, which is the difference between the true value and the expected one.

For the next step it will then identify which variables caused the largest amount of the error. E.g. perhaps most people under 30 don’t earn 50k a year, but those above do. So it will create a decision tree split here that says people under 30 have <50k wage, those above 30 have >50k wage. This is known as a weak learner. It isn’t very informative in itself, and may not be very accurate. However, the algorithm will keep on iterating, testing and adding in new learners until more intricate and significant patterns in the data emerge.

Eventually the algorithm will stop if its met sufficient conditions e.g. it’s no longer gaining any improvement by adding in new trees. A loss function is minimised at each stage to tell us which trees are going to significantly improve the result. The algorithm has tuneable stopping criteria that can improve its performance e.g. how many trees it produces, how many splits of the data it makes within each tree, sensitivity to outlier points.

To make a prediction, each variable is fed in to the model for an observation, and run through all the decision trees made. A weighted average across these trees will then tell us the expected classification.

Implementation: Model Tuning

Fine tune the chosen model. Use grid search (GridSearchCV) with at least one important parameter tuned with at least 3 different values. You will need to use the entire training set for this. In the code cell below, you will need to implement the following: - Import sklearn.grid_search.GridSearchCV and sklearn.metrics.make_scorer. - Initialize the classifier you’ve chosen and store it in clf. - Set a random_state if one is available to the same state you set before. - Create a dictionary of parameters you wish to tune for the chosen model. - Example: parameters = {'parameter' : [list of values]}. - Note: Avoid tuning the max_features parameter of your learner if that parameter is available! - Use make_scorer to create an fbeta_score scoring object (with $\beta = 0.5$). - Perform grid search on the classifier clf using the 'scorer', and store it in grid_obj. - Fit the grid search object to the training data (X_train, y_train), and store it in grid_fit.

Note: Depending on the algorithm chosen and the parameter list, the following implementation may take some time to run!

# TODO: Import 'GridSearchCV', 'make_scorer', and any other necessary libraries
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import make_scorer

# TODO: Initialize the classifier
clf = GradientBoostingClassifier(random_state = 1)

# TODO: Create the parameters list you wish to tune, using a dictionary if needed.
# HINT: parameters = {'parameter_1': [value1, value2], 'parameter_2': [value1, value2]}
parameters = {'max_depth':[3,4,5,6,7]}

# TODO: Make an fbeta_score scoring object using make_scorer()
scorer = make_scorer(fbeta_score, beta = 0.5)

# TODO: Perform grid search on the classifier using 'scorer' as the scoring method using GridSearchCV()
grid_obj = GridSearchCV(estimator = clf, param_grid = parameters, scoring = scorer)

# TODO: 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))

Unoptimized model
------
Accuracy score on testing data: 0.8630
F-score on testing data: 0.7395

Optimized Model
------
Final accuracy score on the testing data: 0.8700
Final F-score on the testing data: 0.7498

Question 5 - Final Model Evaluation

• What is your optimized model’s accuracy and F-score on the testing data?
• Are these scores better or worse than the unoptimized model?
• How do the results from your optimized model compare to the naive predictor benchmarks you found earlier in Question 1?_
  

Note: Fill in the table below with your results, and then provide discussion in the Answer box.

Results:

Metric	Benchmark Predictor	Unoptimized Model	Optimized Model
Accuracy Score	0.2478	0.8630	0.8700
F-score	0.2917	0.7395	0.7498

Answer:

Optimised scores are better than both the benchmark and unoptimised gradient boosting model, for both accuracy and F-score. The parameter optimised is max_depth. This controls the maximum depth of a tree. The default is 3, and the optimised value is 6. We have 103 features after hot-coding. The more splits a tree can make, the more complex interactions it can account for across these features.

---

Feature Importance

An important task when performing supervised learning on a dataset like the census data we study here is determining which features provide the most predictive power. By focusing on the relationship between only a few crucial features and the target label we simplify our understanding of the phenomenon, which is most always a useful thing to do. In the case of this project, that means we wish to identify a small number of features that most strongly predict whether an individual makes at most or more than \$50,000.

Choose a scikit-learn classifier (e.g., adaboost, random forests) that has a feature_importance_ attribute, which is a function that ranks the importance of features according to the chosen classifier. In the next python cell fit this classifier to training set and use this attribute to determine the top 5 most important features for the census dataset.

Question 6 - Feature Relevance Observation

When Exploring the Data, it was shown there are thirteen available features for each individual on record in the census data. Of these thirteen records, which five features do you believe to be most important for prediction, and in what order would you rank them and why?

Answer:

1 & 2: education-num & education. Better education would more often than not allow more opportunities in job positions with higher earnings. I think the education-num variable may be more useful, especially if there are some factors of the education variable that has low quantities.

3: age. as people age they develop and have more opportunities for pay rises and job promotions.

4: occupation. Some sectors will pay better than others based on the skills required and supply/demand for the role.

5: workclass. Some workclasses should exempt people from earning >50k e.g. “Never-worked”

Implementation - Extracting Feature Importance

Choose a scikit-learn supervised learning algorithm that has a feature_importance_ attribute availble for it. This attribute is a function that ranks the importance of each feature when making predictions based on the chosen algorithm.

In the code cell below, you will need to implement the following: - Import a supervised learning model from sklearn if it is different from the three used earlier. - Train the supervised model on the entire training set. - Extract the feature importances using '.feature_importances_'.

# TODO: Train the supervised model on the training set using .fit(X_train, y_train)
# using the optimised model from above
model = best_clf

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

# misc
indices = np.argsort(importances)[::-1]
x = len(indices)
best = indices[0:5]
print X_train.columns.values[best]

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

['capital-gain' 'age' 'marital-status_ Married-civ-spouse' 'capital-loss'
 'education-num']

Question 7 - Extracting Feature Importance

Observe the visualization created above which displays the five most relevant features for predicting if an individual makes at most or above \$50,000.
* How do these five features compare to the five features you discussed in Question 6? * If you were close to the same answer, how does this visualization confirm your thoughts? * If you were not close, why do you think these features are more relevant?

Answer:

Features differ to expectations with capital-gain/loss & marital-status (Married-civ-spouse) appearing in the top 5. For capital-gain & capital-loss, I didn’t select these as I haven’t come across the terminology before. After reading up on them, it makes sense that they have an impact on income. If a person makes a lot of money via selling assets, then they will have earned more income. And similar logic with capital-loss. For marital status, I am still a bit unsure why marriage would have a big impact on an individuals income, unless its confounded with age. If the income is pooled in the data, then this would make sense.

Feature Selection

How does a model perform if we only use a subset of all the available features in the data? With less features required to train, the expectation is that training and prediction time is much lower — at the cost of performance metrics. From the visualization above, we see that the top five most important features contribute more than half of the importance of all features present in the data. This hints that we can attempt to reduce the feature space and simplify the information required for the model to learn. The code cell below will use the same optimized model you found earlier, and train it on the same training set with only the top five important features.

# 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: 0.8700
F-score on testing data: 0.7498

Final Model trained on reduced data
------
Accuracy on testing data: 0.8588
F-score on testing data: 0.7247

Question 8 - Effects of Feature Selection

• How does the final model’s F-score and accuracy score on the reduced data using only five features compare to those same scores when all features are used?

The model results after running with the top 5 variables is very good. We only lose 1.3% accuracy (0.87 to 0.8588) & 3.3% F-score value (0.7498 to 0.7247) after moving to the top 5 variables.

• If training time was a factor, would you consider using the reduced data as your training set?

Yes I think so. Below is code to get the time taken to fit the models with reduced and full training sets respectively. It takes ~2-3 seconds for reduced; ~25-30 seconds for overall. If time is important and interpretation of the model is more important than having the best working model, then the reduced model is more ideal. E.g. if feeding this back for decision making, its easier to say these are the 5 areas to focus on first. As its better than the naive estimate it can also serve as a more informed benchmark model, for further development.

import time
start = time.clock()
clf = (clone(best_clf)).fit(X_train_reduced, y_train) 
print time.clock() - start

import time
start = time.clock()
clf = (clone(best_clf)).fit(X_train, y_train) 
print time.clock() - start 

2.34810586546
28.6414531483