The first thing we need to do is to import all the Python libraries we'll need. The last line of code—%matplotlib inline—is required only if you are running the code in IPython Notebook:

import pandas as pd
import numpy as np
import matplotlib as plt
import matplotlib.pyplot as plt
%matplotlib inline

Next, we define a variable for the full path to our data file. It's recommended to do this so that if the location of your data file changes, you have to update only one line of code:

data_file = '/Users/robertdempsey/Dropbox/private/Python Business Intelligence Cookbook/Data/ISL/College.csv'

Once you have the data file variable, use the read_csv() function provided by Pandas to create a DataFrame from the CSV file:

colleges = pd.read_csv(data_file,
                        sep=',',
                        header=0,
                        index_col=0,
                        parse_dates=True,
                        tupleize_cols=False,
                        error_bad_lines=False,
                        warn_bad_lines=True,
                        skip_blank_lines=True,
                        low_memory=False
                  )

If using IPython Notebook, use the head() function to view the top five rows of the DataFrame. This helps to ensure that the data is imported correctly, and allows us to see some of the data:

colleges.head()

Because this is a new dataset, we use the dtypes function to view the names and types of the columns of the DataFrame:

colleges.dtypes

Next, find out the number of rows and columns contained in the DataFrame using the shape function:

colleges.shape

Next, we create a boxplot of the number of applications and the number of accepted applicants. We do this by calling the boxplot() function on the DataFrame and passing in three arguments:

The resulting plot looks like the following image:

We can immediately see that there are, in fact, outliers in the data. The outliers are those plotted towards the top of the graph.

To better see the outliers, we next create a scatterplot showing the relationship between the application and acceptance numbers:

colleges.plot(kind='scatter',
              x='Accept',
              y='Apps',
              figsize=(16, 6))

This helps confirm that we do indeed have outliers. However, which colleges do those points heading to the top right of the plot represent? To find out, we next label each point.

First we create our plot as we did before:

fig, ax = plt.subplots()
colleges.plot(kind='scatter',
              x='Accept',
              y='Apps',
              figsize=(16, 6),
              ax=ax)

Next, we loop through each row of our DataFrame, assign them labels using the annotate function, and specify the x and y values of the point we want to annotate and its label.

An example annotation would be (Abilene Christian University, 1232, 1660) with the label being Abilene Christian University, the x value (accepted) being 1232, and the y value (apps) being 1660.

for k, v in colleges.iterrows():
    ax.annotate(k,(v['Accept'],v['Apps']))

Finally, we draw the annotated scatterplot as follows:

fig.canvas.draw()

We can now clearly see the two outliers in the data:

If we wanted to see all 777 of the labeled points, we would need make the plot a lot bigger.