Assignment 1
Due: Sunday, September 27
For this assignment you will experiment with Python. NumPy, and Pandas in order to
perform some basic data preprocessing and analysis tasks.
You will work with a modified subset of a real data set of customer for a bank.
The
data is provided in a CSV formatted file with the first row containing the
attribute names. The description of the the different
fields in the data are provided in
this
document. You must only use Python, NumPy,
Pandas, Matplotlib to perform the
tasks for this assignment
 Explore the general characteristics of the data as a
whole: examine the means, standard deviations, and other statistics
associated with the numerical attributes; also show the distributions of
values associated with categorical attributes (for categorical attributes
use Matplotlib library and/or
plotting capabilities of Pandas to generate bar
charts showing the distribution of categories for each attribute).
 Suppose that the hypothetical bank is particularly
interested in customers who buy the PEP (Personal Equity Plan) product.
Compare and contrast the subsets of customers
who buy and don't buy the PEP. Compute summaries (as in part 1) of the
selected data with respect to all other attributes (you do not need to plot
distributions). Can you observe any
significant differences between these segments of customers? Discuss your
observations.
 Use zscore normalization to standardize the values of the
income attribute. [Do not change the original income
attribute or add the normalized income to the table.]
 Discretize the age attribute into 3 categories
(corresponding to "young", "midage", and "old"). [Do not change the
original age attribute or add the discretized age to the table.]
 Use MinMax Normalization to transform
the values of all numeric attributes (income, age, children)
in the original table onto the range 0.01.0.
 Convert the table (after normalization in part 5) into the
standard spreadsheet format. Note that this requires converting
each categorical attribute into multiple binary ("dummy") attributes (one for each values of
the categorical attribute) and assigning binary values corresponding to the
presence or not presence of the attribute value in the original record).
The numeric attributes should remain unchanged. Save this new table into a
file called bank_numeric.csv and submit it along with your
assignment.
 Using the numeric data set with the dummy variables (of the previous part), perform basic
correlation
analysis among the attributes. Discuss your results by indicating any
significant positive or negative correlations among pairs of attributes. You need to
construct a complete Correlation Matrix. Be sure to first remove the
Customer ID column before creating the correlation matrix. [Hint:
you can create the correlation matrix by using the corr()
function in Pandas or corrcoef
function in NumPy].
 Create a scatter plot of the (nonnormalized)
Income attribute relative to Age. Be sure that
your plot contains appropriate labels for the axes. Do these variables seem
correlated?
 Create histograms for (nonnormalized) Income (using 9 bins) and
Age (using 15 bins).
 Perform a crosstabulation of the region
attribute with the pep attribute. This requires the aggregation of the
occurrences of each pep value (yes or no) separately for each value of the
region attribute. Show the results as a 4 by 2 (region x pep) table with entries representing the
counts. [Hint: you can either use Numpy or use aggregations functions in
Pandas such as groupby() and crosstab().] Then,
either using Matplotlib directly or the plot() function in
Pandas create a bar chart graph to visualize of the
relationships between these sets of variables. [Hint:
This example of creating simple bar charts using Matplotlib may be
useful.]
 Now consider a modified version of the bank data that
contains missing values (bank_data_missing_vals.csv).
(a) Using Pandas determine all the attributes with missing values and the
number of missing values for each such attribute. (b) Show all the instances
in the data that contain a missing value. (c) Fill the missing values for
all numeric attributes using the mean value for the attribute. (d) After
filling in the missing numeric values, drop all rows where a categorical
attribute contains a missing value. (e) Show that the final resulting table
does not contain missing values.
Notes on Submission: You must submit your Jupyter Notebook
(similar to examples in class) which includes your documented code, results of
your interactions, and any discussions or explanations of the results. Please
organize your notebook so that it's clear what parts of the notebook correspond
to which problems in the assignment. Please submit the notebook in both IPYNB
and HTML formats (along with any auxiliary files). Your assignment should be submitted
via D2L.
