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.
Your goal for this project is to identify students who might need early intervention before they fail to graduate. Which type of supervised learning problem is this, classification or regression? Why?
Answer: It is a classification problem, since the output we are trying to predict has a discrete value, this is, whether the student does o does not need an intervention.
If the variable to predict were continuous, a more suitable choice would have been a regression classifier.
Run the code cell below to load necessary Python libraries and load the student data. Note that the last column from this dataset, 'passed', will be our target label (whether the student graduated or didn't graduate). All other columns are features about each student.
# 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!"
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 (%).# TODO: Calculate number of students
n_students = student_data.shape[0]
# TODO: Calculate number of features
n_features = student_data.shape[1]-1 #substracted the target column
# TODO: Calculate passing students
n_passed = student_data[student_data["passed"]=='yes'].shape[0]
# TODO: Calculate failing students
n_failed = student_data[student_data["passed"]=='no'].shape[0]
# TODO: Calculate graduation rate
grad_rate = 100.* float(n_passed)/float(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)
print student_data.head()
print student_data[student_data["passed"]=='yes'].shape[0]
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.
# 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.
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.# TODO: Import any additional functionality you may need here
from sklearn import cross_validation
# 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 = cross_validation.train_test_split( X_all, y_all, test_size=float(num_test)/float(X_all.shape[0]), random_state=42)
# 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.
List three supervised learning models that are appropriate for this problem. What are the general applications of each model? What are their strengths and weaknesses? Given what you know about the data, why did you choose these models to be applied?
Answer: I picked three different algorithms with a very different nature: one is very easy to understand and makes classifications based on questions (DTs), another acts like a switch, given a result once certain conditions are fulfilled (logistic regression) and the last one it is a powerful tool that can separate classes of data, extending the understandable 2D separation problem to up to n-features considered.
Decision trees
-Why I elected it: DTs can be used in classification and regression problems. The dataset is a mixture of numerical and categorical data and DTs are appropiate for this (see strengths).
DT is one of the simplest algorithms for classification and I thought it would be reasonable to compare the behavior of other algorithms to its. It can give an insight of the problem and can provide good results with little effort.
Logistic regression
-Why I elected it: Linear regressions (logistic regression belongs to that family) are appropiate for linearly related data (I do no not expect to exist any other kind o relationship between the students features) and are very fast.
One think I like about logistic regression is how it is capable of classifying binary problems. I used to think of it as a threshold but implemented with a really good function which will allow use to much more, as implementing gradient descent. And plus, it is roughly a preceptron! It can be trained with different classes and give binary output (our target is Passed: yes/no) given the result activates or not the threshold.
Support Vector Machines
-Why I elected it: SVMs are appropiate when the number of features is high.
What I really liked about SVM is how it is capable of finding boundaries between data even up to n-dimensions! The 2D explanation is very intuitive and we can see how different groups are separated by a gap. SVM takes it further and increase the combination of features taken into account in the decission. And, an amazing thing, is how space transformation (that thing we studied in vertorial calculus and complex maths) can be of good use to have an easily linearly separated problem.
https://en.wikipedia.org/wiki/Support_vector_machine http://scikit-learn.org/stable/modules/svm.html http://cbcl.mit.edu/cbcl/publications/ps/iccv2001.pdf
http://www.edvancer.in/logistic-regression-vs-decision-trees-vs-svm-part2/
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.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.# TODO: Import the three supervised learning models from sklearn
# from sklearn import model_A
from sklearn import tree
# from sklearn import model_B
from sklearn.linear_model import LogisticRegression
# from skearln import model_C
from sklearn import svm
# TODO: Initialize the three models
clf_A = tree.DecisionTreeClassifier(random_state = 1)
clf_B = LogisticRegression(random_state = 3)
clf_C = svm.SVC(random_state = 5)
list_of_clf=[clf_A, clf_B, clf_C]
# 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 i,clf in enumerate(list_of_clf):
print "Classifier %d ..." %(i+1)
train_predict(clf, X_train_100, y_train_100, X_test, y_test)
train_predict(clf, X_train_200, y_train_200, X_test, y_test)
train_predict(clf, X_train_300, y_train_300, X_test, y_test)
print "\n"
Classifer 1 - Decision Tree Classifier
| Training Set Size | Training Time | Prediction Time (test) | F1 Score (train) | F1 Score (test) |
|---|---|---|---|---|
| 100 | 0.0009 | 0.0002 | 1.0 | 0.6154 |
| 200 | 0.0012 | 0.0003 | 1.0 | 0.7419 |
| 300 | 0.0032 | 0.0002 | 1.0 | 0.6720 |
Classifer 2 - Logistic Regression
| Training Set Size | Training Time | Prediction Time (test) | F1 Score (train) | F1 Score (test) |
|---|---|---|---|---|
| 100 | 0.0012 | 0.0002 | 0.8593 | 0.7647 |
| 200 | 0.0021 | 0.0003 | 0.8562 | 0.7914 |
| 300 | 0.0033 | 0.0002 | 0.8468 | 0.8060 |
Classifer 3 - Suppor Vector Machines (SVM)
| Training Set Size | Training Time | Prediction Time (test) | F1 Score (train) | F1 Score (test) |
|---|---|---|---|---|
| 100 | 0.0014 | 0.0010 | 0.8777 | 0.7746 |
| 200 | 0.0030 | 0.0015 | 0.8679 | 0.7815 |
| 300 | 0.0066 | 0.0022 | 0.8761 | 0.7838 |
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: Based in the previous experiments F1 score the ranking of algorithms will be: Logistic Regression, SVMs and Decision Trees.
Based in the prediction time times for the biggest training dataset the ranking of algorithms will be: Logistic Regression, Decision Tree and SVMs.
It is clear the best performance is given by Logistic Regression.
In one to two paragraphs, explain to the board of directors in layman's terms how the final model chosen is supposed to work. For example if you've chosen to use a decision tree or a support vector machine, how does the model go about making a prediction?
Answer: The model chosen is logistic regression. It belongs to the group of the linear models. The logistic regression is characterized by a set of input features (failures, absences, age, gender...) and a target feature (passed or not passed). The set of input features or variables are 30 in this case.
In order to start the process, the data is splitted into training and testing subsets. The tranining subset is used so the model can learn based on the previous experience to give answers to future cases. The test subset is used for checking how good the model will be at predicting whether new students will or will not pass. It is a way of having the answers to check how good our model generalizes with data it does not know yet.
The logistic regression is then trained with the training dataset and try to give a prediction based on the combination of the features that describe the data. The combination of features (or characteristic of the data) is weighted, so as to give more importance to certain features (i.e. failures and absences will be more important thant number of siblings in order to determine whether the student will pass or not). The objetive when training the model is to minimize the error between the predicted and the real value.
In the case of logistic regression this process uses an exponential function in which the linear combination is introduced.
Once the model is trained, it is time to make predictions and determine whether totally unknown student passed or not given the experience accumulated by training the model with the already known students. The features of each new student will be weighted with the values founf in the training processes, combined and the introduced in the logistic function, which will tell if the student has more or less probabilities of passing given what it has learned from previous cases.
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.# TODO: Import 'GridSearchCV' and 'make_scorer'
from sklearn.grid_search import GridSearchCV
from sklearn.metrics import make_scorer, f1_score
# TODO: Create the parameters list you wish to tune
parameters = {'penalty': ['l1','l2'], 'C': [0.001, 0.01, 0.1, 1, 10, 100, 1000] , 'max_iter': [10,25,50],
'fit_intercept': [True, False] , 'intercept_scaling': [0.1, 1, 10, 100, 1000, 10000], 'n_jobs': [2] }
# TODO: Initialize the classifier
clf = LogisticRegression()
# TODO: Make an f1 scoring function using 'make_scorer'
f1_scorer = make_scorer(f1_score, pos_label = 'yes')
print f1_scorer
# TODO: Perform grid search on the classifier using the f1_scorer as the scoring method
grid_obj = GridSearchCV(clf, param_grid= parameters, scoring = f1_scorer)
# TODO: Fit the grid search object to the training data and find the optimal parameters
grid_obj.fit(X_train, y_train)
# Get the estimator
clf = grid_obj.best_estimator_
print clf
# 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))
What is the final model's F1 score for training and testing? How does that score compare to the untuned model?
Answer:
The final's $F_1$ score for the tuned model for training is 0.8323 and for testing 0.7891, and for the untuned model the $F_1$ score for training is 0.8468 and for testing 0.8060.
The $F_1$ score is worse for the tuned model, meaning we are able to generalize better. Additional parameters would be required to check the validity of the parameters chosen by gridsearch
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.