Welcome to the first project of the Machine Learning Engineer Nanodegree! In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. 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.
In this project, you will evaluate the performance and predictive power of a model that has been trained and tested on data collected from homes in suburbs of Boston, Massachusetts. A model trained on this data that is seen as a good fit could then be used to make certain predictions about a home — in particular, its monetary value. This model would prove to be invaluable for someone like a real estate agent who could make use of such information on a daily basis.
The dataset for this project originates from the UCI Machine Learning Repository. The Boston housing data was collected in 1978 and each of the 506 entries represent aggregated data about 14 features for homes from various suburbs in Boston, Massachusetts. For the purposes of this project, the following preprocessing steps have been made to the dataset:
'MEDV'
value of 50.0. These data points likely contain missing or censored values and have been removed.'RM'
value of 8.78. This data point can be considered an outlier and has been removed.'RM'
, 'LSTAT'
, 'PTRATIO'
, and 'MEDV'
are essential. The remaining non-relevant features have been excluded.'MEDV'
has been multiplicatively scaled to account for 35 years of market inflation.Run the code cell below to load the Boston housing dataset, along with a few of the necessary Python libraries required for this project. You will know the dataset loaded successfully if the size of the dataset is reported.
# Import libraries necessary for this project
import numpy as np
import pandas as pd
from sklearn.model_selection import ShuffleSplit
# Import supplementary visualizations code visuals.py
import visuals as vs
# Pretty display for notebooks
%matplotlib inline
# Load the Boston housing dataset
data = pd.read_csv('housing.csv')
prices = data['MEDV']
features = data.drop('MEDV', axis = 1)
# Success
print("Boston housing dataset has {} data points with {} variables each.".format(*data.shape))
In this first section of this project, you will make a cursory investigation about the Boston housing data and provide your observations. Familiarizing yourself with the data through an explorative process is a fundamental practice to help you better understand and justify your results.
Since the main goal of this project is to construct a working model which has the capability of predicting the value of houses, we will need to separate the dataset into features and the target variable. The features, 'RM'
, 'LSTAT'
, and 'PTRATIO'
, give us quantitative information about each data point. The target variable, 'MEDV'
, will be the variable we seek to predict. These are stored in features
and prices
, respectively.
For your very first coding implementation, you will calculate descriptive statistics about the Boston housing prices. Since numpy
has already been imported for you, use this library to perform the necessary calculations. These statistics will be extremely important later on to analyze various prediction results from the constructed model.
In the code cell below, you will need to implement the following:
'MEDV'
, which is stored in prices
.# TODO: Minimum price of the data
minimum_price = np.min(prices)
# TODO: Maximum price of the data
maximum_price = np.max(prices)
# TODO: Mean price of the data
mean_price = np.mean(prices)
# TODO: Median price of the data
median_price = np.median(prices)
# TODO: Standard deviation of prices of the data
std_price = np.std(prices)
# Show the calculated statistics
print("Statistics for Boston housing dataset:\n")
print("Minimum price: ${:,.2f}".format(minimum_price))
print("Maximum price: ${:,.2f}".format(maximum_price))
print("Mean price: ${:,.2f}".format(mean_price))
print("Median price ${:,.2f}".format(median_price))
print("Standard deviation of prices: ${:,.2f}".format(std_price))
As a reminder, we are using three features from the Boston housing dataset: 'RM'
, 'LSTAT'
, and 'PTRATIO'
. For each data point (neighborhood):
'RM'
is the average number of rooms among homes in the neighborhood.'LSTAT'
is the percentage of homeowners in the neighborhood considered "lower class" (working poor).'PTRATIO'
is the ratio of students to teachers in primary and secondary schools in the neighborhood. Using your intuition, for each of the three features above, do you think that an increase in the value of that feature would lead to an increase in the value of 'MEDV'
or a decrease in the value of 'MEDV'
? Justify your answer for each.
Hint: This problem can phrased using examples like below.
'RM'
value(number of rooms) of 6 be worth more or less than a home that has an 'RM'
value of 7?'LSTAT'
value(percent of lower class workers) of 15 have home prices be worth more or less than a neighborhood that has an 'LSTAT'
value of 20?'PTRATIO'
value(ratio of students to teachers) of 10 have home prices be worth more or less than a neighborhood that has an 'PTRATIO'
value of 15?Answer:
In this second section of the project, you will develop the tools and techniques necessary for a model to make a prediction. Being able to make accurate evaluations of each model's performance through the use of these tools and techniques helps to greatly reinforce the confidence in your predictions.
It is difficult to measure the quality of a given model without quantifying its performance over training and testing. This is typically done using some type of performance metric, whether it is through calculating some type of error, the goodness of fit, or some other useful measurement. For this project, you will be calculating the coefficient of determination, R2, to quantify your model's performance. The coefficient of determination for a model is a useful statistic in regression analysis, as it often describes how "good" that model is at making predictions.
The values for R2 range from 0 to 1, which captures the percentage of squared correlation between the predicted and actual values of the target variable. A model with an R2 of 0 is no better than a model that always predicts the mean of the target variable, whereas a model with an R2 of 1 perfectly predicts the target variable. Any value between 0 and 1 indicates what percentage of the target variable, using this model, can be explained by the features. A model can be given a negative R2 as well, which indicates that the model is arbitrarily worse than one that always predicts the mean of the target variable.
For the performance_metric
function in the code cell below, you will need to implement the following:
r2_score
from sklearn.metrics
to perform a performance calculation between y_true
and y_predict
.score
variable.# TODO: Import 'r2_score'
from sklearn.metrics import r2_score
def performance_metric(y_true, y_predict):
""" Calculates and returns the performance score between
true and predicted values based on the metric chosen. """
# TODO: Calculate the performance score between 'y_true' and 'y_predict'
score = r2_score(y_true, y_predict)
# Return the score
return score
Assume that a dataset contains five data points and a model made the following predictions for the target variable:
True Value | Prediction |
---|---|
3.0 | 2.5 |
-0.5 | 0.0 |
2.0 | 2.1 |
7.0 | 7.8 |
4.2 | 5.3 |
Run the code cell below to use the performance_metric
function and calculate this model's coefficient of determination.
# Calculate the performance of this model
score = performance_metric([3, -0.5, 2, 7, 4.2], [2.5, 0.0, 2.1, 7.8, 5.3])
print("Model has a coefficient of determination, R^2, of {:.3f}.".format(score))
Hint: The R2 score is the proportion of the variance in the dependent variable that is predictable from the independent variable. In other words:
Answer:
R2 score also knowns as coeeficient of determination is a number in range of [0, 1] where 0 represents that there is no correlation between the dependent variable and the independent vairbale. 1 represents that the dependent variable is correlated to the independent vairbale and dependent vairbale can be predicted with a very high accuracy using the independent vairbale.
A score of 0.923 represents that 92.3% of variability in the dependent variable is accountable using the independent variable (high correlation). In the data displayed, it is clear that there is general correlation, as the independent vairbale(true value increases) so does the dependent variable (predicted value). So we can clearly state that the the model successfully captured (much part of) the trend in the target variable
Your next implementation requires that you take the Boston housing dataset and split the data into training and testing subsets. Typically, the data is also shuffled into a random order when creating the training and testing subsets to remove any bias in the ordering of the dataset.
For the code cell below, you will need to implement the following:
train_test_split
from sklearn.cross_validation
to shuffle and split the features
and prices
data into training and testing sets.random_state
for train_test_split
to a value of your choice. This ensures results are consistent.X_train
, X_test
, y_train
, and y_test
.# TODO: Import 'train_test_split'
from sklearn.model_selection import train_test_split
import time
# TODO: Shuffle and split the data into training and testing subsets
X_train, X_test, y_train, y_test = train_test_split(features, prices, test_size=0.2, random_state=10)
# Success
print("Training and testing split was successful.")
Hint: Think about how overfitting or underfitting is contingent upon how splits on data is done.
Answer:
Any Machine Learning approach must take into account the trade-off between variance and bias (in other words overfitting and underfitting). A model always learn from a set of data. This data may or may not be a general display of the trend in the population from which it is taken. In the world of software development, testing is always a crucial part. This train and test set split gives us a way to train our model over the majority of data and to see whether it is performing aptly on unseen (or alien) values or not. There arrives two cases where the system might produce bad results:
This problem is captured by performing test over the trained model to check its real world implications over alien data points.
In this third section of the project, you'll take a look at several models' learning and testing performances on various subsets of training data. Additionally, you'll investigate one particular algorithm with an increasing 'max_depth'
parameter on the full training set to observe how model complexity affects performance. Graphing your model's performance based on varying criteria can be beneficial in the analysis process, such as visualizing behavior that may not have been apparent from the results alone.
The following code cell produces four graphs for a decision tree model with different maximum depths. Each graph visualizes the learning curves of the model for both training and testing as the size of the training set is increased. Note that the shaded region of a learning curve denotes the uncertainty of that curve (measured as the standard deviation). The model is scored on both the training and testing sets using R2, the coefficient of determination.
Run the code cell below and use these graphs to answer the following question.
# Produce learning curves for varying training set sizes and maximum depths
vs.ModelLearning(features, prices)
Hint: Are the learning curves converging to particular scores? Generally speaking, the more data you have, the better. But if your training and testing curves are converging with a score above your benchmark threshold, would this be necessary? Think about the pros and cons of adding more training points based on if the training and testing curves are converging.
Answer:
Taking into account the graph with max_depth = 3
As more and more training points are added:
Both the curves clearly seems to get saturated at an r2 score of approximately 0.8 for 300 data points or more in training set. Adding more points will clearly add an overhead of running the model over the data even though there is no need as the model is at peak score for max_depth=3
The following code cell produces a graph for a decision tree model that has been trained and validated on the training data using different maximum depths. The graph produces two complexity curves — one for training and one for validation. Similar to the learning curves, the shaded regions of both the complexity curves denote the uncertainty in those curves, and the model is scored on both the training and validation sets using the performance_metric
function.
Run the code cell below and use this graph to answer the following two questions Q5 and Q6.
vs.ModelComplexity(X_train, y_train)
Hint: High bias is a sign of underfitting(model is not complex enough to pick up the nuances in the data) and high variance is a sign of overfitting(model is by-hearting the data and cannot generalize well). Think about which model(depth 1 or 10) aligns with which part of the tradeoff.
Answer:
Looking at the curve it is clear that the score over both the training and the validation set was low at depth 1, depicting that the model was unable to get a better sense of the trend in the data through training. In other words the system went into underfitting. Thus at depth 1 the system suffered high bias problem.
As the depth increased we see a general trend of increase in the performance over the training set. However the performance began to drop over the testing set (cross validations) at the depths greater than 4. At the depth of 10 there is a huge gap in the training score and the validation score. This clearly depicts that model was performing exceptionally well over the training set but performed very poorly over the cross validations. This gap in the learning curves is in itself the case of overfitting. Thus at depth 10 the system suffered high variance problem.
Hint: Look at the graph above Question 5 and see where the validation scores lie for the various depths that have been assigned to the model. Does it get better with increased depth? At what point do we get our best validation score without overcomplicating our model? And remember, Occams Razor states "Among competing hypotheses, the one with the fewest assumptions should be selected."
Answer:
Looking at the complexity curves it is clear that the x coordinate of the peak of the validation curve best genralizes over the validation set while at the same time giving a near good performance on the training set. The peak value at which we get this best generalization is depth=4.
In this final section of the project, you will construct a model and make a prediction on the client's feature set using an optimized model from fit_model
.
Hint: When explaining the Grid Search technique, be sure to touch upon why it is used, what the 'grid' entails and what the end goal of this method is. To solidify your answer, you can also give an example of a parameter in a model that can be optimized using this approach.
Answer:
Grid Search Technique
A grid search technique is generally a mechanism of finding the best possible combination of values (from set of values provided) for the hyperparameters of a learning algorithm. Going into it in lay man terms we can say that grid search is an algorithm to find a way and get another algorithm to work more efficiently.
We can explain this by using the example of a simple Support Vector Classifier(SVC) from the sklearn library. Let us say we want to make it work more efficiently over a set of data. The way to do this is to choose the hyperparameters aptly. If we want to do this using the values of C and gamma only. We can select a set of values for C and gamma and generate a grid. For example,
C | gamma |
---|---|
1 | 0.1 |
10 | 0.2 |
100 | 0.5 |
1000 | 1.0 |
The grid search algorithm will take in the scoring function (to check the best possible combination) the dataset as well as the object of the SVC and will result the values of gamma and c which will give us the best possible value of the SVC.
NOTE: The values might be like 10, 1.0 that is it may or may not return a row as result. Also C column might be having only 3 possible values while gamma might be having 4 or more.
What is the k-fold cross-validation training technique?
What benefit does this technique provide for grid search when optimizing a model?
Hint: When explaining the k-fold cross validation technique, be sure to touch upon what 'k' is, how the dataset is split into different parts for training and testing and the number of times it is run based on the 'k' value.
When thinking about how k-fold cross validation helps grid search, think about the main drawbacks of grid search which are hinged upon using a particular subset of data for training or testing and how k-fold cv could help alleviate that. You can refer to the docs for your answer.
Answer:
k-fold cross Validation
K-fold cross validation is a technique for validating the working of a model over the alien data. In this technique we divide the available dataset into k equal parts and run the algorithm k times over the training and test dataset. Here training dataset equal to k-1 parts of the k parts we got from division of data and the test dataset is the kth part of the original data. This means the algorithm is ran for testing over each part of the original dataset atleast once. The overall score of the model is then computed as the average score of the model over the k sets.
k-fold can help in techniques like grid search to get to the results of the best values for hyperparamters by providing different training and test sets everytime. But the shuffling of the data points in the set before slicing it in k parts is necessary. Reason for shuffling lies in the order in which we recieve or gather our dataset. If the dataset, for example, is in order it might be possible that the training set gets all the values of one type of data (In the case of our dataset it might be possible that data is ordered in terms of LSTAT). This will result in model to generalize well over some kind of data while missing over other data points.
Your final implementation requires that you bring everything together and train a model using the decision tree algorithm. To ensure that you are producing an optimized model, you will train the model using the grid search technique to optimize the 'max_depth'
parameter for the decision tree. The 'max_depth'
parameter can be thought of as how many questions the decision tree algorithm is allowed to ask about the data before making a prediction. Decision trees are part of a class of algorithms called supervised learning algorithms.
In addition, you will find your implementation is using ShuffleSplit()
for an alternative form of cross-validation (see the 'cv_sets'
variable). While it is not the K-Fold cross-validation technique you describe in Question 8, this type of cross-validation technique is just as useful!. The ShuffleSplit()
implementation below will create 10 ('n_splits'
) shuffled sets, and for each shuffle, 20% ('test_size'
) of the data will be used as the validation set. While you're working on your implementation, think about the contrasts and similarities it has to the K-fold cross-validation technique.
Please note that ShuffleSplit has different parameters in scikit-learn versions 0.17 and 0.18.
For the fit_model
function in the code cell below, you will need to implement the following:
DecisionTreeRegressor
from sklearn.tree
to create a decision tree regressor object.'regressor'
variable.'max_depth'
with the values from 1 to 10, and assign this to the 'params'
variable.make_scorer
from sklearn.metrics
to create a scoring function object.performance_metric
function as a parameter to the object.'scoring_fnc'
variable.GridSearchCV
from sklearn.grid_search
to create a grid search object.'regressor'
, 'params'
, 'scoring_fnc'
, and 'cv_sets'
as parameters to the object. GridSearchCV
object to the 'grid'
variable.# TODO: Import 'make_scorer', 'DecisionTreeRegressor', and 'GridSearchCV'
from sklearn.metrics import make_scorer
from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import GridSearchCV
def fit_model(X, y):
""" Performs grid search over the 'max_depth' parameter for a
decision tree regressor trained on the input data [X, y]. """
# Create cross-validation sets from the training data
# sklearn version 0.18: ShuffleSplit(n_splits=10, test_size=0.1, train_size=None, random_state=None)
# sklearn versiin 0.17: ShuffleSplit(n, n_iter=10, test_size=0.1, train_size=None, random_state=None)
cv = ShuffleSplit(n_splits = 10, test_size = 0.2, random_state = 10)
# TODO: Create a decision tree regressor object
regressor = DecisionTreeRegressor()
# TODO: Create a dictionary for the parameter 'max_depth' with a range from 1 to 10
params = {'max_depth': range(1, 11)}
# TODO: Transform 'performance_metric' into a scoring function using 'make_scorer'
scoring_fnc = make_scorer(performance_metric)
# TODO: Create the grid search cv object --> GridSearchCV()
# Make sure to include the right parameters in the object:
# (estimator, param_grid, scoring, cv) which have values 'regressor', 'params', 'scoring_fnc', and 'cv_sets' respectively.
grid = GridSearchCV(regressor, param_grid=params, scoring=scoring_fnc, cv=cv)
# Fit the grid search object to the data to compute the optimal model
grid = grid.fit(X, y)
# Return the optimal model after fitting the data
return grid.best_estimator_
Once a model has been trained on a given set of data, it can now be used to make predictions on new sets of input data. In the case of a decision tree regressor, the model has learned what the best questions to ask about the input data are, and can respond with a prediction for the target variable. You can use these predictions to gain information about data where the value of the target variable is unknown — such as data the model was not trained on.
Run the code block below to fit the decision tree regressor to the training data and produce an optimal model.
# Fit the training data to the model using grid search
reg = fit_model(X_train, y_train)
# Produce the value for 'max_depth'
print("Parameter 'max_depth' is {} for the optimal model.".format(reg.get_params()['max_depth']))
Hint: The answer comes from the output of the code snipped above.
Answer:
Optimal Depth of model equals 4. My intuition hit the point with the optimal depth for the model. The complexity curve gives a clear insight of how well the model can work with increasing complexities and can saturate and then get a dip in performance after a while.
Imagine that you were a real estate agent in the Boston area looking to use this model to help price homes owned by your clients that they wish to sell. You have collected the following information from three of your clients:
Feature | Client 1 | Client 2 | Client 3 |
---|---|---|---|
Total number of rooms in home | 5 rooms | 4 rooms | 8 rooms |
Neighborhood poverty level (as %) | 17% | 32% | 3% |
Student-teacher ratio of nearby schools | 15-to-1 | 22-to-1 | 12-to-1 |
Hint: Use the statistics you calculated in the Data Exploration section to help justify your response. Of the three clients, client 3 has has the biggest house, in the best public school neighborhood with the lowest poverty level; while client 2 has the smallest house, in a neighborhood with a relatively high poverty rate and not the best public schools.
Run the code block below to have your optimized model make predictions for each client's home.
# Produce a matrix for client data
client_data = [[5, 17, 15], # Client 1
[4, 32, 22], # Client 2
[8, 3, 12]] # Client 3
# Show predictions
for i, price in enumerate(reg.predict(client_data)):
print("Predicted selling price for Client {}'s home: ${:,.2f}".format(i+1, price))
Answer:
The recommended prices:
An optimal model is not necessarily a robust model. Sometimes, a model is either too complex or too simple to sufficiently generalize to new data. Sometimes, a model could use a learning algorithm that is not appropriate for the structure of the data given. Other times, the data itself could be too noisy or contain too few samples to allow a model to adequately capture the target variable — i.e., the model is underfitted.
Run the code cell below to run the fit_model
function ten times with different training and testing sets to see how the prediction for a specific client changes with respect to the data it's trained on.
vs.PredictTrials(features, prices, fit_model, client_data)
Hint: Take a look at the range in prices as calculated in the code snippet above. Some questions to answering:
Answer:
The model should not be used as it is in a real-world setting. There are more than one reasons to believe this:
Relevancy (in 2017):
According to Zillow
The median home value in Boston is \$558,300. Boston home values have gone up 11.5% over the past year and Zillow predicts they will rise 4.5% within the next year. This can be found here.
This clearly displays that a price from 39 years old dataset is totally out of comparison and is irrelevant to today's price range. Also there might be variation in values of 'LSTAT', 'RM' and 'PTRATIO' of locality over 39 years.
Features:
Many features like price per square feet, crime rate in the locality and the age of the building along with the 3 features we used are some more possible values that can give model a way to be more precise in predicting house prices.
Robustness
As seen in the sensitivity section, the model produces values in range of \$41k for same values of input. This clearly depicts lack of robustness of model over the data and the lack of its generalization over the dataset.
Applicability
A model trained on dataset of a well-off place have certain standards which far bests the standards of a rural area.
Fairness
It is clearly fair to judge price of a house based on the entire neighborhood as a person will take into account the facilities available to him/her and how well all his needs will be fulfilled after spending loads of money.
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.