Scribd
Upload
41 views

Data Analysis and Visualisation With Python

Uploaded by

dhurgadevi
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
41 views

Data Analysis and Visualisation With Python

Uploaded by

dhurgadevi
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 42

Exploratory data analysis (EDA)

Exploring your data is a crucial step in data analysis. It involves:


Organising the data set
Plotting aspects of the data set
Maybe producing some numerical summaries; central tendency and spread,
etc.

“Exploratory data analysis can never be the whole story, but nothing else can
serve as the foundation stone.”
- John Tukey.
Download the data
Download the Pokemon dataset from:

https://github.com/LewBrace/da_and_vis_python

Unzip the folder, and save the data file in a location you’ll remember.
Reading in the data
First we import the Python packages we are going to use.
Then we use Pandas to load in the dataset as a data frame.

NOTE: The argument index_col argument states that we'll treat the first
column of the dataset as the ID column.
NOTE: The encoding argument allows us to by pass an input error created
by special characters in the data set.
Examine the data set
We could spend time staring at these
numbers, but that is unlikely to offer us
any form of insight.
We could begin by conducting all of our
statistical tests.
However, a good field commander never
goes into battle without first doing a
recognisance of the terrain…
This is exactly what EDA is for…
Plotting a histogram in Python
Bins
 You may have noticed the two histograms we’ve seen so far look different,
despite using the exact same data.
 This is because they have different bin values.
 The left graph used the default bins generated by plt.hist(), while the one on the
right used bins that I specified.
There are a couple of ways to manipulate bins in matplotlib.
Here, I specified where the edges of the bars of the histogram are; the bin
edges.
You could also specify the number of bins, and Matplotlib will automatically
generate a number of evenly spaced bins.
Seaborn
Matplotlib is a powerful, but sometimes unwieldy, Python library.
Seaborn provides a high-level interface to Matplotlib and makes it easier to
produce graphs like the one on the right.
Some IDEs incorporate elements of this “under the hood” nowadays.
Benefits of Seaborn
Seaborn offers:
- Using default themes that are aesthetically pleasing.
- Setting custom colour palettes.
- Making attractive statistical plots.
- Easily and flexibly displaying distributions.
- Visualising information from matrices and DataFrames.
The last three points have led to Seaborn becoming the exploratory data
analysis tool of choice for many Python users.
Plotting with Seaborn
One of Seaborn's greatest strengths is its diversity of plotting functions.
Most plots can be created with one line of code.
For example….
Histograms
Allow you to plot the distributions of numeric variables.
Other types of graphs: Creating a scatter plot

Name of our
Name of variable we dataframe fed to the
want on the x-axis “data=“ command

Seaborn “linear Name of variable we


model plot” want on the y-axis
function for
creating a scatter
graph
Seaborn doesn't have a dedicated scatter plot function.
We used Seaborn's function for fitting and plotting a regression line; hence
lmplot()
However, Seaborn makes it easy to alter plots.
To remove the regression line, we use the fit_reg=False command
The hue function
Another useful function in Seaborn is the hue function, which enables us to
use a variable to colour code our data points.
Factor plots
Make it easy to separate plots by categorical classes.

Colour by stage.
Separate by stage.
Generate using a swarmplot.
Rotate axis on x-ticks by 45 degrees.
A box plot
The total, stage, and legendary entries are not combat stats so we should remove
them.
Pandas makes this easy to do, we just create a new dataframe
We just use Pandas’ .drop() function to create a dataframe that doesn’t include the
variables we don’t want.
Seaborn’s theme
Seaborn has a number of themes you can use to alter the appearance of
plots.
For example, we can use “whitegrid” to add grid lines to our boxplot.
Violin plots
Violin plots are useful alternatives to box plots.
They show the distribution of a variable through the thickness of the violin.
Here, we visualise the distribution of attack by Pokémon's primary type:
• Dragon types tend to have higher Attack stats than Ghost types, but they also have greater
variance. But there is something not right here….
• The colours!
Seaborn’s colour palettes
Seaborn allows us to easily set custom colour palettes by providing it with
an ordered list of colour hex values.
We first create our colours list.
Then we just use the palette= function and feed in our colours list.
Because of the limited number of observations, we could also use a swarm
plot.
Here, each data point is an observation, but data points are grouped
together by the variable listed on the x-axis.
Overlapping plots
Both of these show similar information, so it might be useful to overlap
them.
Set size of print canvas.

Remove bars from inside the violins

Make bars black and slightly transparent

Give the graph a title


Data wrangling with Pandas
What if we wanted to create such a plot that included all of the other stats
as well?
In our current dataframe, all of the variables are in different columns:
If we want to visualise all stats, then we’ll have to “melt” the dataframe.

We use the .drop() function again to re-


create the dataframe without these three
variables.
The dataframe we want to melt.

The variables to keep, all others will be


melted.
A name for the new, melted, variable.

• All 6 of the stat columns have been "melted" into one, and
the new Stat column indicates the original stat (HP, Attack,
Defense, Sp. Attack, Sp. Defense, or Speed).
• It's hard to see here, but each pokemon now has 6 rows of
data; hende the melted_df has 6 times more rows of data.
This graph could be made to look nicer with a few tweaks.

Enlarge the plot.

Separate points by hue.


Use our special Pokemon colour palette.
Adjust the y-axis.
Move the legend box outside of
the graph and place to the right of
it..
Plotting all data: Empirical cumulative distribution
functions (ECDFs)

An alternative way of visualising a


distribution of a variable in a large dataset is
to use an ECDF.
Here we have an ECDF that shows the
percentages of different attack strengths of
pokemon.
An x-value of an ECDF is the quantity you
are measuring; i.e. attacks strength.
The y-value is the fraction of data points that
have a value smaller than the corresponding
x-value. For example…
75% of Pokemon have an attack
level of 90 or less

20% of Pokemon have an attack


level of 50 or less.
Plotting an ECDF
You can also plot multiple ECDFs on
the same plot.
As an example, here with have an
ECDF for Pokemon attack, speed,
and defence levels.
We can see here that defence levels
tend to be a little less than the other
two.
The usefulness of ECDFs
It is often quite useful to plot the ECDF first as part of your workflow.
It shows all the data and gives a complete picture as to how the data are
distributed.
Heatmaps
Useful for visualising matrix-like data.
Here, we’ll plot the correlation of the stats_df variables
Bar plot
Visualises the distributions of categorical variables.

Rotates the x-ticks 45 degrees


Joint Distribution Plot
Joint distribution plots combine information from scatter plots and histograms to
give you detailed information for bi-variate distributions.
Any questions?

You might also like