-
Notifications
You must be signed in to change notification settings - Fork 3
/
tc52_visualization1&2.py
115 lines (62 loc) · 2.57 KB
/
tc52_visualization1&2.py
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
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
# -*- coding: utf-8 -*-
"""TC52_visualization1&2.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1MTTyHpyL29zfXcyqsuWQuLy4Ru3FlQ_l
"""
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
"""Importing and Displaying Data"""
df = sns.load_dataset('titanic')
df.head()
df.shape
df.describe()
"""Checking Null Values"""
df.isnull().sum()
"""Data preprocessing"""
df.drop('age', axis=1, inplace= True)
df.drop('deck', axis = 1, inplace = True)
df.drop('embarked', axis = 1, inplace = True)
df
df.isnull().sum()
sns.histplot(data = df, x = 'fare', binwidth=30)
sns.histplot(data = df, x ='fare', kde=True, binwidth = 30)
sns.histplot(data = df, x ='fare', hue= 'pclass', binwidth=25 )
sns.histplot(data= df, x='sex', hue='alive', binwidth=30)
sns.histplot(data = df, x = 'fare', hue='sex', binwidth=30)
sns.distplot(df['fare'])
sns.distplot(df['fare'], kde= False, bins= 15)
sns.displot(data=df, x= 'fare', multiple = 'dodge', col= 'pclass', binwidth=24)
sns.displot(data=df, x='fare', col= 'pclass', hue='sex', multiple ='dodge', binwidth=25)
"""Assingment 2 visualization"""
df1 = sns.load_dataset('titanic')
df1['age'].fillna(df1['age'].mean(), inplace = True)
df1.drop('deck', axis = 1, inplace = True)
df1.drop('embarked', axis = 1, inplace = True)
df1.drop('embark_town', axis = 1, inplace = True)
df1.isnull().sum()
sns.boxplot(x = 'sex' , y= 'age', data=df1)
sns.boxplot(x = 'age' , y= 'sex', hue='survived', data=df1)
sns.boxplot(x = 'age' , y= 'sex', data=df1)
sns.boxplot(x= 'age', y='sex', hue='survived', data=df1)
sns.barplot(x='sex', y='age', data=df1)
sns.barplot(x='pclass', y='age', data=df1)
sns.barplot(x='sex', y='age', hue='pclass', data=df1)
sns.barplot(x='pclass', y='age', hue='sex', data=df1)
sns.barplot(x='sex', y='fare',data=df1)
sns.barplot(x='age', y='fare',data=df1)
sns.countplot(x='sex', data=df1)
df2=sns.load_dataset('titanic')
df2.head()
sns.catplot(x='embarked', y='age', hue='survived', data=df2)
sns.violinplot(x='sex', y='age', data=df2)
sns.stripplot(x='sex',y='age', data=df2)
sns.stripplot(x='sex',y='age', hue='survived', data=df2)
sns.stripplot(x='sex',y='age', hue='survived', data=df2, split=True)
sns.swarmplot(x='sex', y='age', data=df2, hue='survived')
sns.swarmplot(x='sex', y='age', data=df2, hue='survived', split=True)
sns.swarmplot(x='pclass', y='age', data=df2, hue='survived', split=True)
sns.violinplot(x='sex', y='age', data=df2)
sns.swarmplot(x='sex', y='age', data=df2, hue='survived',color='black' ,split=True)