Welcome to the second project of the Machine Learning Engineer Nanodegree! In this notebook, some template code has already been provided for you, and it will be your job to implement the additional functionality necessary to successfully complete this project. Sections that begin with 'Implementation' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section and the specifics of the implementation are marked in the code block with a 'TODO'
statement. Please be sure to read the instructions carefully!
In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question X' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.
Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. In addition, Markdown cells can be edited by typically double-clicking the cell to enter edit mode.
Answer: This is a case of classification problem as we need to classify students to two groups - the one who need intervention vs others.
In [6]:
# Import libraries
import numpy as np
import pandas as pd
from time import time
from sklearn.metrics import f1_score
# Read student data
student_data = pd.read_csv("student-data.csv")
print "Student data read successfully!"
rand_seed = 25 # To be used throughout the notebook
Let's begin by investigating the dataset to determine how many students we have information on, and learn about the graduation rate among these students. In the code cell below, you will need to compute the following:
n_students
.n_features
.n_passed
.n_failed
.grad_rate
, in percent (%).
In [7]:
# TODO: Calculate number of students
n_students = len(student_data)
# TODO: Calculate number of features
n_features = len(student_data.columns) - 1
# TODO: Calculate passing students
n_passed = sum([1 if x == 'yes' else 0 for x in student_data['passed'] ])
# TODO: Calculate failing students
n_failed = n_students - n_passed
# TODO: Calculate graduation rate
grad_rate = n_passed * 100.0 / n_students
# Print the results
print "Total number of students: {}".format(n_students)
print "Number of features: {}".format(n_features)
print "Number of students who passed: {}".format(n_passed)
print "Number of students who failed: {}".format(n_failed)
print "Graduation rate of the class: {:.2f}%".format(grad_rate)
In this section, we will prepare the data for modeling, training and testing.
It is often the case that the data you obtain contains non-numeric features. This can be a problem, as most machine learning algorithms expect numeric data to perform computations with.
Run the code cell below to separate the student data into feature and target columns to see if any features are non-numeric.
In [8]:
# Extract feature columns
feature_cols = list(student_data.columns[:-1])
# Extract target column 'passed'
target_col = student_data.columns[-1]
# Show the list of columns
print "Feature columns:\n{}".format(feature_cols)
print "\nTarget column: {}".format(target_col)
# Separate the data into feature data and target data (X_all and y_all, respectively)
X_all = student_data[feature_cols]
y_all = student_data[target_col]
# Show the feature information by printing the first five rows
print "\nFeature values:"
print X_all.head()
As you can see, there are several non-numeric columns that need to be converted! Many of them are simply yes
/no
, e.g. internet
. These can be reasonably converted into 1
/0
(binary) values.
Other columns, like Mjob
and Fjob
, have more than two values, and are known as categorical variables. The recommended way to handle such a column is to create as many columns as possible values (e.g. Fjob_teacher
, Fjob_other
, Fjob_services
, etc.), and assign a 1
to one of them and 0
to all others.
These generated columns are sometimes called dummy variables, and we will use the pandas.get_dummies()
function to perform this transformation. Run the code cell below to perform the preprocessing routine discussed in this section.
In [9]:
def preprocess_features(X):
''' Preprocesses the student data and converts non-numeric binary variables into
binary (0/1) variables. Converts categorical variables into dummy variables. '''
# Initialize new output DataFrame
output = pd.DataFrame(index = X.index)
# Investigate each feature column for the data
for col, col_data in X.iteritems():
# If data type is non-numeric, replace all yes/no values with 1/0
if col_data.dtype == object:
col_data = col_data.replace(['yes', 'no'], [1, 0])
# If data type is categorical, convert to dummy variables
if col_data.dtype == object:
# Example: 'school' => 'school_GP' and 'school_MS'
col_data = pd.get_dummies(col_data, prefix = col)
# Collect the revised columns
output = output.join(col_data)
return output
X_all = preprocess_features(X_all)
print "Processed feature columns ({} total features):\n{}".format(len(X_all.columns), list(X_all.columns))
So far, we have converted all categorical features into numeric values. For the next step, we split the data (both features and corresponding labels) into training and test sets. In the following code cell below, you will need to implement the following:
X_all
, y_all
) into training and testing subsets.random_state
for the function(s) you use, if provided.X_train
, X_test
, y_train
, and y_test
.
In [10]:
# TODO: Import any additional functionality you may need here
from sklearn.cross_validation import train_test_split
# TODO: Set the number of training points
num_train = 300
# Set the number of testing points
num_test = X_all.shape[0] - num_train
# TODO: Shuffle and split the dataset into the number of training and testing points above
#X_train = None
#X_test = None
#y_train = None
#y_test = None
(X_train, X_test, y_train, y_test ) = train_test_split(X_all,y_all, train_size = num_train, random_state = rand_seed)
# 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])
In this section, you will choose 3 supervised learning models that are appropriate for this problem and available in scikit-learn
. You will first discuss the reasoning behind choosing these three models by considering what you know about the data and each model's strengths and weaknesses. You will then fit the model to varying sizes of training data (100 data points, 200 data points, and 300 data points) and measure the F1 score. You will need to produce three tables (one for each model) that shows the training set size, training time, prediction time, F1 score on the training set, and F1 score on the testing set.
The following supervised learning models are currently available in scikit-learn
that you may choose from:
List three supervised learning models that are appropriate for this problem. For each model chosen
Answer: Running some basic experiments and visualizations (saved in Experiement.ipynb in same folder), shows that the data points are not linearly separable.
I have choosen following tree models -
[1] http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html
[2] https://en.wikipedia.org/wiki/Naive_Bayes_classifier
[3] https://en.wikipedia.org/wiki/Gradient_boosting#Usage
[4] https://databricks.com/blog/2015/01/21/random-forests-and-boosting-in-mllib.html
[8] http://people.revoledu.com/kardi/tutorial/KNN/Strength%20and%20Weakness.htm
Run the code cell below to initialize three helper functions which you can use for training and testing the three supervised learning models you've chosen above. The functions are as follows:
train_classifier
- takes as input a classifier and training data and fits the classifier to the data.predict_labels
- takes as input a fit classifier, features, and a target labeling and makes predictions using the F1 score.train_predict
- takes as input a classifier, and the training and testing data, and performs train_clasifier
and predict_labels
.
In [11]:
def train_classifier(clf, X_train, y_train):
''' Fits a classifier to the training data. '''
# Start the clock, train the classifier, then stop the clock
start = time()
clf.fit(X_train, y_train)
end = time()
# Print the results
print "Trained model in {:.4f} seconds".format(end - start)
def predict_labels(clf, features, target):
''' Makes predictions using a fit classifier based on F1 score. '''
# Start the clock, make predictions, then stop the clock
start = time()
y_pred = clf.predict(features)
end = time()
# Print and return results
print "Made predictions in {:.4f} seconds.".format(end - start)
return f1_score(target.values, y_pred, pos_label='yes')
def train_predict(clf, X_train, y_train, X_test, y_test):
''' Train and predict using a classifer based on F1 score. '''
# Indicate the classifier and the training set size
print "Training a {} using a training set size of {}. . .".format(clf.__class__.__name__, len(X_train))
# Train the classifier
train_classifier(clf, X_train, y_train)
# Print the results of prediction for both training and testing
print "F1 score for training set: {:.4f}.".format(predict_labels(clf, X_train, y_train))
print "F1 score for test set: {:.4f}.".format(predict_labels(clf, X_test, y_test))
With the predefined functions above, you will now import the three supervised learning models of your choice and run the train_predict
function for each one. Remember that you will need to train and predict on each classifier for three different training set sizes: 100, 200, and 300. Hence, you should expect to have 9 different outputs below — 3 for each model using the varying training set sizes. In the following code cell, you will need to implement the following:
clf_A
, clf_B
, and clf_C
.random_state
for each model you use, if provided.X_train
and y_train
.
In [12]:
# TODO: Import the three supervised learning models from sklearn
# from sklearn import model_A
# from sklearn import model_B
# from skearln import model_C
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.neighbors import KNeighborsClassifier
# TODO: Initialize the three models
clf_A = GaussianNB()
clf_B = GradientBoostingClassifier()
clf_C = KNeighborsClassifier()
# TODO: Set up the training set sizes
X_train_100 = X_train[0:100]
y_train_100 = y_train[0:100]
X_train_200 = X_train[0:200]
y_train_200 = y_train[0:200]
X_train_300 = X_train[0:300]
y_train_300 = y_train[0:300]
# TODO: Execute the 'train_predict' function for each classifier and each training set size
# train_predict(clf, X_train, y_train, X_test, y_test)
for model in (clf_A, clf_B, clf_C):
for dataset in ((X_train_100,y_train_100), (X_train_200, y_train_200), (X_train_300,y_train_300)):
train_predict(model, dataset[0], dataset[1], X_test, y_test)
Edit the cell below to see how a table can be designed in Markdown. You can record your results from above in the tables provided.
Classifer 1 - GaussianNB
Training Set Size | Training Time | Prediction Time (test) | F1 Score (train) | F1 Score (test) |
---|---|---|---|---|
100 | 0.0024 | 0.0010 | 0.8550 | 0.7481 |
200 | 0.0020 | 0.0009 | 0.8321 | 0.7132 |
300 | 0.0039 | 0.0013 | 0.8088 | 0.7500 |
Classifer 2 - GradientBoostingClassifier
Training Set Size | Training Time | Prediction Time (test) | F1 Score (train) | F1 Score (test) |
---|---|---|---|---|
100 | 0.1647 | 0.0011 | 1.000 | 0.7761 |
200 | 0.2048 | 0.0010 | 0.9852 | 0.7879 |
300 | 0.2362 | 0.0010 | 0.9740 | 0.7727 |
Classifer 3 - KNeighborsClassifier
Training Set Size | Training Time | Prediction Time (test) | F1 Score (train) | F1 Score (test) |
---|---|---|---|---|
100 | 0.0012 | 0.0038 | 0.7972 | 0.7068 |
200 | 0.0018 | 0.0039 | 0.8571 | 0.7121 |
300 | 0.0016 | 0.0057 | 0.8722 | 0.7482 |
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 F1 score.
Based on the experiments you performed earlier, in one to two paragraphs, explain to the board of supervisors what single model you chose as the best model. Which model is generally the most appropriate based on the available data, limited resources, cost, and performance?
Answer: - I would choose KNearest Neighbour model over the other two based on following reasoning -
Based on the above table of observations on F1 score (training and test), Gradient Boost seem to be overfitting data. So we should avoid GB model for this problem. Test F1 score for GaussianNB and KNearestNeighbour are quite close and shows both models performed well on the task. The training and test score are a bit appart which may point to that the size of dataset was not enough to learn bring training and error to be approx same.
The above table shows that the time to train model is two order of magnitute higher for Gradient boost algorithms than the other two. KNearestNeighbour outperforms GaussianNB in the training time and hence will be more useful in
Given that the performance of GaussianNB and KNN is similar, I would prefer to pick KNN as this provides slight edge in training time and does not depend on the assumption that the features are independent.
In one to two paragraphs, explain to the board of directors 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 or technical jargon, such as describing equations or discussing the algorithm implementation.
Answer: In summary, K Nearest Neighbour works by looking at k data points which are nearest and assign the class of most occuring class in the chosen data points.
Although there is no training phase for KNNs, this phase is used to set up data structures to speed up the prediction phase.
To assign a class to a new data point, we calculate the distance of the data point to all the other points. Then k points with min distance are chosen to new point. Then the resulting class of the new data point is calcualted based on the max num of class of other k-near points.
One of the initial step is setting up parameters. The most important parameter for the model is how many datapoint we want to look at locally for making a prediction. This parameter is called K. This parameter determines the performance and computational cost of the algorithm. If K is chosen small, the model may not generalize well and hence accuracy may be low. If we choose K higher, the accuracy should generally increase but it becomes more computationally expensive.
In the discussion above we did not define the meaning of distance amoung the data points. A function has to be defined as the distance function between datapoints. If the features are all numerical, distance function be simple euclidian distance between the points. In case some features are strings, we may need to define distance based on the either num of characters, amount of difference in two strings or perhaps based on semantics of the words. There are other distance has to be used in domain-specific case like distance between two genomes may be the number of neucletides it differ etc.
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:
sklearn.grid_search.gridSearchCV
and sklearn.metrics.make_scorer
.parameters = {'parameter' : [list of values]}
.clf
.make_scorer
and store it in f1_scorer
.pos_label
parameter to the correct value!clf
using f1_scorer
as the scoring method, and store it in grid_obj
.X_train
, y_train
), and store it in grid_obj
.
In [15]:
# TODO: Import 'GridSearchCV' and 'make_scorer'
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import make_scorer
from sklearn.metrics import f1_score
# TODO: Create the parameters list you wish to tune
parameters = {'n_neighbors':[3,5,7,9], 'algorithm' : ['auto', 'ball_tree', 'kd_tree', 'brute']}
# TODO: Initialize the classifier
clf = KNeighborsClassifier()
# TODO: Make an f1 scoring function using 'make_scorer'
f1_scorer = make_scorer(f1_score, pos_label = 'yes')
# TODO: Perform grid search on the classifier using the f1_scorer as the scoring method
grid_obj = GridSearchCV(clf, parameters, f1_scorer)
# TODO: Fit the grid search object to the training data and find the optimal parameters
grid_obj = grid_obj.fit(X_train,y_train)
# Get the estimator
clf = grid_obj.best_estimator_
# Report the final F1 score for training and testing after parameter tuning
print "Tuned model has a training F1 score of {:.4f}.".format(predict_labels(clf, X_train, y_train))
print "Tuned model has a testing F1 score of {:.4f}.".format(predict_labels(clf, X_test, y_test))
Answer: The final F1 score for testing is 0.797 and 0.748 respectively for tuned and untuned KNN model. This shows performance boost we can get by iterating through the parameter space and finding best hyperparameters. The F1 score for training for tuned and untuned model is 0.842 and 0.872 respectively.
Note: Once you have completed all of the code implementations and successfully answered each question above, you may finalize your work by exporting the iPython Notebook as an HTML document. You can do this by using the menu above and navigating to
File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.