# Exploratory Data Analysis in Python – Part II

Articles From: QuantInsti
Website: QuantInsti

QuantInsti

Read Part I to get started with the Python packages and datasets.

You can also find the standard deviation and the variance with the “statistics” package. The Python code is shown below:

import statistics as st

print(“Variance of the Closing price is % s”
%(st.variance(tesla[‘Close’])))
print(“Standard Deviation of Closing Price is % s ”
% (st.stdev(tesla[‘Close’])))

The output is as follows:

Univariate graphical method

Let me ask you a question, have you ever asked a friend for directions to their house and felt confused. Sure they are giving the right directions, “Take a left turn at XYZ Mall and a right at the ABC Bank” etc., but you can’t help feeling that it could be better. What if the friend gives you a map and says they have circled the destination in red.”

Well, the map sounds better right? Most of us are quick to learn something if we have a visual in front of us than plain numbers in a table.

Hence, we will take the earlier example, and do a line plot of the closing price to see the trend in the market.

The Python code is as follows:

import matplotlib.pyplot as plt
tesla[‘Close’].plot(figsize=(10,7))
plt.legend()
plt.grid()
plt.show()

You can also use the histogram to see the distribution. We will find the daily returns and plot its histogram.

Let’s see the histogram:

tesla[‘daily_returns’].dropna()
plt.hist(tesla[‘daily_returns’], bins = 5)

Since it is a small data set, we can’t really infer anything meaningful here. In contrast, if we do a histogram of Tesla for the last year, we will find it as follows: