ExploratoryDataAnalysis/Relative Frequency Analysis.py at main · reemadata/ExploratoryDataAnalysis · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
# -*- coding: utf-8 -*-
"""Welcome to Colab

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/notebooks/intro.ipynb
"""

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# first Qualitative
# use Titanic from seaborn
titanic = sns.load_dataset("titanic")

# relative frequency
freq = titanic["sex"].value_counts(normalize=True)
print(freq)

# Bar graph
freq.plot(kind="bar", title="Relative Frequency - Sex")
plt.show()

# Pie chart
freq.plot(kind="pie", autopct="%.2f%%", title="Relative Frequency - Sex")
plt.ylabel("")
plt.show()


# Second Quantitative
iris = sns.load_dataset("iris")

# Cumulative frequency graph (petal_length)
iris["petal_length"].sort_values().reset_index(drop=True).plot(drawstyle="steps-post", title="Cumulative Frequency - Petal Length")
plt.show()

# Cumulative relative frequency
iris["petal_length"].sort_values().reset_index(drop=True).div(len(iris)).plot(drawstyle="steps-post", title="Cumulative Relative Frequency - Petal Length")
plt.show()

# Scatter plot (petal_length vs petal_width)
plt.scatter(iris["petal_length"], iris["petal_width"])
plt.xlabel("Petal Length")
plt.ylabel("Petal Width")
plt.title("Scatter Plot - Petal Length vs Width")
plt.show()