In 

[1]: import pandas as pd

import numpy as np

from scipy.stats import norm

import matplotlib.pyplot as plt

import seaborn as sns

Line Plot

In [2]: days = [1,2,3,4,5,6,7,8,9,10,11,12,13,14,15]

temperature = [36.6,37,37.7,39,40.1,43,43.4,45,45.6,40.1,44,45,46.8,47,47.8]

temp_df = pd.DataFrame({'days':days,'temperature': temperature})

sns.lineplot(x = 'days',y = 'temperature',data = temp_df)

plt.show()

In [3]: tips_df = pd.read_csv('tips.csv')

tips_df.head()

Out[3]: t o t al_bill t ip sex smo ker day t ime size

0 16.99 1.01 Female No Sun Dinner 2

1 10.34 1.66 Male No Sun Dinner 3

2 21.01 3.50 Male No Sun Dinner 3

3 23.68 3.31 Male No Sun Dinner 2

4 24.59 3.61 Female No Sun Dinner 4

In [4]: sns.lineplot(x = 'total_bill',y = 'tip',data = tips_df)

plt.show()

In [5]: plt.figure(figsize = (15,9))

sns.set(style = 'darkgrid')

sns.lineplot(x = 'size',y = 'total_bill',data = tips_df,hue = 'sex',style =

# plt.title()

plt.title('Line Plot',fontsize = 25,color = 'black')

plt.xlabel('Size',fontsize = 15)

plt.ylabel('Total Bill',fontsize = 15)

plt.legend(loc = 2)

plt.show()

In [6]: plt.figure(figsize = (15,9))

sns.set(style = 'darkgrid')

sns.lineplot(x = 'size',y = 'total_bill',data = tips_df,hue = 'day',style =

# plt.title()

plt.title('Line Plot',fontsize = 25,color = 'black')

plt.xlabel('Size',fontsize = 15)

plt.ylabel('Total Bill',fontsize = 15)

plt.legend(loc = 2)

plt.show()

In [7]: plt.figure(facecolor = 'yellow')

ax = plt.axes()

ax.set_facecolor('black')

# plt.figure(figsize = (15,9))

sns.set(style = 'darkgrid')

sns.lineplot(x = 'size',y = 'total_bill',data = tips_df,hue = 'day',style =

# plt.title()

plt.title('Line Plot',fontsize = 25,color = 'black')

plt.xlabel('Size',fontsize = 15,color = 'red')

plt.ylabel('Total Bill',fontsize = 15,color = 'red')

plt.legend(loc = 2)

plt.show()

Histogram & Distplot

In [8]: tips_df.head()

Out[8]: t o t al_bill t ip sex smo ker day t ime size

0 16.99 1.01 Female No Sun Dinner 2

1 10.34 1.66 Male No Sun Dinner 3

2 21.01 3.50 Male No Sun Dinner 3

3 23.68 3.31 Male No Sun Dinner 2

4 24.59 3.61 Female No Sun Dinner 4

In [9]: sns.distplot(tips_df['size'])

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
In [10]: sns.distplot(tips_df['tip'])

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)

In [11]: sns.distplot(tips_df['total_bill'],hist = False)

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`kdeplot` (an axes-level function for kernel density plots).
warnings.warn(msg, FutureWarning)
In [12]: sns.distplot(tips_df['total_bill'],kde = False)

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)

In [13]: sns.distplot(tips_df['total_bill'],fit = norm,hist = False,color = 'red') #,r

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`kdeplot` (an axes-level function for kernel density plots).
warnings.warn(msg, FutureWarning)
In [14]: sns.distplot(tips_df['total_bill'],fit = norm,hist = True,color = 'red',axlab
plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)

In [15]: sns.distplot(tips_df['total_bill'],vertical = True)

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:1689: FutureWarning: The `vertical` parameter
is deprecated and will be removed in a future version. Assign the data to th
e `y` variable instead.
warnings.warn(msg, FutureWarning)
In [16]: # plt.figure(facecolor = 'red')

# ax = plt.axes()

# ax.set_facecolor('black')

plt.figure(figsize = (15,9))

sns.distplot(tips_df['total_bill'],color = 'red',axlabel = 'Total Bill') #,ru

plt.title('Bill Graph')

plt.legend('Total Bill')

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)

In [17]: plt.figure(facecolor = 'red')

ax = plt.axes()

ax.set_facecolor('black')

 # plt.figure(figsize = (15,9))

sns.distplot(tips_df['total_bill'],color = 'white',axlabel = 'Total Bill') #,

plt.title('Bill Graph')

plt.legend('Total Bill')

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)

In [18]: tips_df.total_bill.sort_values()

67 3.07
Out[18]:
92 5.75
111 7.25
172 7.25
149 7.51
...
182 45.35
156 48.17
59 48.27
212 48.33
170 50.81
Name: total_bill, Length: 244, dtype: float64

In [19]: # bins = [1,5,10,15,20,25,30,35,40,45,50,55]

# plt.figure(figsize = (15,9))

sns.distplot(tips_df['total_bill'],color = 'white',axlabel = 'Total Bill',his

plt.title('Bill Graph')

# plt.xticks(bins)

plt.legend('Total Bill')

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
In [20]: plt.figure(facecolor = 'pink')

ax = plt.axes()

ax.set_facecolor('black')

sns.distplot(tips_df['total_bill'],color = 'white',axlabel = 'Total Bill',his

plt.title('Bill Graph')

# plt.xticks(bins)

plt.legend('Total Bill')

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)

In [21]: plt.figure(facecolor = 'yellow')

ax = plt.axes()

ax.set_facecolor('black')

sns.distplot(tips_df['total_bill'],color = 'red',axlabel = 'Total Bill',

hist_kws = {'color': 'red','linewidth': 2,'linest

kde_kws = {'color': 'green','linewidth': 2,'l
rug = True,rug_kws = {'color': 'blue','li
plt.title('Bill Graph')

 # plt.xticks(bins)

plt.legend('Total Bill')

plt.grid(color = 'pink',linestyle = '--',linewidth = 1)

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2103: FutureWarning: The `axis` variable is no
longer used and will be removed. Instead, assign variables directly to `x` o
r `y`.
warnings.warn(msg, FutureWarning)

Bar Plot

In [22]: tips_df.head()

Out[22]: t o t al_bill t ip sex smo ker day t ime size

0 16.99 1.01 Female No Sun Dinner 2

1 10.34 1.66 Male No Sun Dinner 3

2 21.01 3.50 Male No Sun Dinner 3

3 23.68 3.31 Male No Sun Dinner 2

4 24.59 3.61 Female No Sun Dinner 4

In [23]: sns.barplot(x = tips_df.day,y = tips_df.total_bill)

plt.show()

In [24]: sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df)

plt.show()

In [25]: order = ['Sun','Thur','Fri','Sat']

hue_order = ['Male','Female']

sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,order = ord

plt.show()

In [26]: # Mean

sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,estimator =

plt.show()

In [27]: # Max

sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,estimator =

plt.show()

In [28]: # STD

sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,estimator =

plt.show()

In [29]: # Sum

sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,estimator =

plt.show()

In [30]: # Min

sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,estimator =

plt.show()

In [31]: # sns.barplot(x = tips_df.day,y = tips_df.total_bill,estimator = np.mean)

# plt.show()

In [32]: # sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,ci = 10,n_b

# plt.show()

In [33]: # sns.barplot(y = 'day',x = 'total_bill',hue = 'sex',data = tips_df)

In [34]: # sns.barplot(x = 'total_bill',y = 'size',hue = 'sex',data = tips_df,orient =

In [35]: # sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,palette =

In [36]: # sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,saturation

In [37]: # sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,capsize = 1

In [38]: # sns.barplot(x = 'day',y = 'total_bill',hue = 'sex',data = tips_df,dodge = Fal

In [39]: kwargs = {'alpha': 0.7,'linestyle':':','linewidth':3,'edgecolor':'black'}

sns.barplot(x = 'day',y = 'total_bill',data = tips_df,**kwargs) # ,hue = 'sex

plt.show()

In [40]: sns.barplot(x = 'day',y = 'total_bill',data = tips_df,alpha = .05,linestyle =

plt.show()

In [41]: ax = sns.barplot(x = 'day',y = 'total_bill',data = tips_df,

alpha = .9,linestyle = '-.',linewidth = 2,

edgecolor = 'black',errcolor = 'black',

errwidth = 2)

ax.set(title = 'Barplot Of Tips DataFrame',

xlabel = 'Days',

ylabel = 'Total Bill')

[Text(0.5, 1.0, 'Barplot Of Tips DataFrame'),

Out[41]:
Text(0.5, 0, 'Days'),
Text(0, 0.5, 'Total Bill')]

In [42]: plt.figure(figsize = (16,9))

sns.barplot(x = 'day',y = 'total_bill',data = tips_df,

alpha = .9,linestyle = '-.',linewidth = 2,

edgecolor = 'black',errcolor = 'black',

errwidth = 2)

plt.title('Barplot Of Tips DataFrame',fontsize = 20,color = 'blue')

plt.xlabel('Days',fontsize = 15,color = 'blue')

plt.ylabel('Total Bill',fontsize = 15,color = 'blue')

# plt.savefig()

plt.show()

In [43]: plt.figure(facecolor = 'pink')

ax = plt.axes()

ax.set_facecolor('white')

#plt.figure(figsize = (16,9))

sns.barplot(x = 'day',y = 'total_bill',data = tips_df,

alpha = .9,linestyle = '-.',linewidth = 1,

edgecolor = 'black',errcolor = 'black',

errwidth = 1)

plt.title('Barplot Of Tips DataFrame',fontsize = 15,color = 'red')

plt.xlabel('Days',fontsize = 10,color = 'red')

plt.ylabel('Total Bill',fontsize = 10,color = 'red')

plt.grid(color = 'red',linestyle = '--',linewidth = 1)

# plt.savefig()

plt.show()

Scatter Plot
In [44]: titanic_df = pd.read_csv('titanic.csv')

titanic_df.head()

Out[44]: survived pclass sex age sibsp parch f are embarked class who adult _male de

0 0 3 male 22.0 1 0 7.2500 S T hird man T rue N

1 1 1 female 38.0 1 0 71.2833 C First woman False

2 1 3 female 26.0 0 0 7.9250 S T hird woman False N

3 1 1 female 35.0 1 0 53.1000 S First woman False

4 0 3 male 35.0 0 0 8.0500 S T hird man T rue N

In [45]: sns.scatterplot(x = 'age',y = 'fare',data = titanic_df,hue = 'sex')

plt.show()

In [46]: plt.figure(figsize = (15,9))

sns.scatterplot(x = 'age',y = 'fare',data = titanic_df,hue = 'sex',style = 'w

plt.show()

In [47]: # plt.figure(figsize = (15,9))

# sns.scatterplot(x = 'who',y = 'fare',data = titanic_df,hue = 'alive',style =

# plt.show()

In [48]: plt.figure(figsize = (15,9))

sns.scatterplot(x = 'who',y = 'fare',data = titanic_df,

hue = 'alive',style = 'alive',size = 'who',

sizes = (50,100),palette = 'inferno',alpha = .7)

plt.show()

In [49]: # plt.figure(facecolor = 'pink')

 # ax = plt.axes()

# ax.set_facecolor('white')

# sns.scatterplot(x = 'age',y = 'fare',data = titanic_df,hue = 'sex')

# plt.grid(color = 'black',linestyle = '--',linewidth = 1)

# plt.show()

Heatmap

In [50]: arr_2d = np.linspace(1,5,12).reshape(4,3)

arr_2d

array([[1. , 1.36363636, 1.72727273],

Out[50]:
[2.09090909, 2.45454545, 2.81818182],
[3.18181818, 3.54545455, 3.90909091],
[4.27272727, 4.63636364, 5. ]])

In [51]: sns.heatmap(arr_2d)

plt.show()

In [52]: globalwarming_df = pd.read_csv('Who_is_responsible_for_global_warming.csv')

globalwarming_df.head()

Out[52]: Co unt ry Co unt ry Indicat o r

Indicat o r Co de 2000 2001 2002 2003
Name Co de Name

CO2
emissions
United
0 USA (metric EN.AT M.CO2E.PC 20.178751 19.636505 19.613404 19.564105
States
tons per
capita)

CO2
emissions
United
1 GBR (metric EN.AT M.CO2E.PC 9.199549 9.233175 8.904123 9.053278
Kingdom
tons per
capita)

CO2
emissions
2 India IND (metric EN.AT M.CO2E.PC 0.979870 0.971698 0.967381 0.992392
tons per
capita)

CO2
emissions
3 China CHN (metric EN.AT M.CO2E.PC 2.696862 2.742121 3.007083 3.524074
tons per
capita)

CO2
emissions
Russian
4 RUS (metric EN.AT M.CO2E.PC 10.627121 10.669603 10.715901 11.090647
Federation
tons per
capita)

In [53]: globalwarming_df = globalwarming_df.drop(columns =['Country Code','Indicator

globalwarming_df.head()

Out[53]: 2000 2001 2002 2003 2004 2005 2006 20

Co unt ry
Name

Unit ed
20.178751 19.636505 19.613404 19.564105 19.658371 19.591885 19.094067 19.2178
St at es

Unit ed
9.199549 9.233175 8.904123 9.053278 8.989140 8.982939 8.898710 8.617
Kingdo m

India 0.979870 0.971698 0.967381 0.992392 1.025028 1.068563 1.121982 1.1932

China 2.696862 2.742121 3.007083 3.524074 4.037991 4.523178 4.980314 5.3349

Russian
10.627121 10.669603 10.715901 11.090647 11.120627 11.253529 11.669122 11.6724
Federat io n

In [54]: plt.figure(figsize = (15,9))

sns.heatmap(globalwarming_df)

plt.show()

In [55]: # plt.figure(figsize = (15,9))

# sns.heatmap(globalwarming_df,vmin = 0,vmax = 21,cmap = 'coolwarm')

# plt.show()

In [56]: plt.figure(figsize = (15,9))

sns.heatmap(globalwarming_df,vmin = 0,vmax = 21,cmap = 'coolwarm',annot = Tru

plt.show()

In [88]: # annot_arr = np.array([['a00','a01','a02'],['a10','a11','a12'],['a20','a21','a

# annot_arr

In [87]: # sns.heatmap(arr_2d,annot = annot_arr,fmt = 's')

# plt.show()

In [86]: # plt.figure(figsize = (15,9))

# annot_kws = {'fontsize': 10,'fontstyle': 'italic','color': 'black','alpha': 0

# sns.heatmap(globalwarming_df,vmin = 0,vmax = 21,cmap = 'coolwarm',annot = Tru
# plt.show()

In [60]: plt.figure(figsize = (15,9))

sns.heatmap(globalwarming_df,vmin = 0,vmax = 21,cmap = 'coolwarm',annot = Tru

plt.show()

In [61]: # plt.figure(figsize = (15,9))

# sns.heatmap(globalwarming_df,cbar = False,xticklabels = False,yticklabels = F

# plt.show()

In [62]: # plt.figure(figsize=(14,14))

# cbar_kws = {"orientation":"horizontal",

# "shrink":1,

# 'extend':'min',

# 'extendfrac':0.1,

# "ticks":np.arange(0,22),

# "drawedges":True,

# }

# sns.heatmap(globalwarming_df, cbar_kws=cbar_kws)

# plt.show()

In [63]: # plt.figure(figsize=(16,9))

# ax = sns.heatmap(globalwarming_df,)

# ax.set(title="Heatmap",

# xlabel="Years",

# ylabel="Country Name",)

# sns.set(font_scale=2) # set fontsize 2

Correlation
In [64]: globalwarming_df.corr()

Out[64]: 2000 2001 2002 2003 2004 2005 2006 2007 2008

2000 1.000000 0.999632 0.999155 0.998911 0.998314 0.997008 0.994087 0.992283 0.987767

2001 0.999632 1.000000 0.999229 0.999026 0.998095 0.996628 0.993860 0.991532 0.987057

2002 0.999155 0.999229 1.000000 0.998907 0.998399 0.997391 0.995643 0.994017 0.990034

2003 0.998911 0.999026 0.998907 1.000000 0.999568 0.998887 0.996614 0.995277 0.991681

2004 0.998314 0.998095 0.998399 0.999568 1.000000 0.999701 0.998105 0.997144 0.993891

2005 0.997008 0.996628 0.997391 0.998887 0.999701 1.000000 0.998942 0.998420 0.995803

2006 0.994087 0.993860 0.995643 0.996614 0.998105 0.998942 1.000000 0.999570 0.998415

2007 0.992283 0.991532 0.994017 0.995277 0.997144 0.998420 0.999570 1.000000 0.999088

2008 0.987767 0.987057 0.990034 0.991681 0.993891 0.995803 0.998415 0.999088 1.000000

2009 0.980143 0.978912 0.983584 0.984511 0.987300 0.990125 0.994104 0.995724 0.998145

2010 0.979172 0.978562 0.982944 0.984466 0.987668 0.990498 0.994985 0.996367 0.998539

2011 0.967887 0.967206 0.972479 0.975128 0.979061 0.982646 0.988553 0.990928 0.994593

2012 0.961582 0.961625 0.967161 0.969919 0.974094 0.977758 0.984892 0.986978 0.991128

2013 0.962466 0.962827 0.967573 0.971053 0.975276 0.978611 0.984857 0.986819 0.989983

2014 0.962331 0.961622 0.965665 0.970508 0.975061 0.978521 0.983371 0.986199 0.988927

In [65]: # plt.figure(figsize=(16,9))

# ax = sns.heatmap(globalwarming_df.corr(),annot = True,linewidths = 2)

# ax.tick_params(size = 5,color = 'white',labelsize = 5,labelcolor = 'white')

# plt.title('Heatmap of Who is Responsible for Global Warming',fontsize = 20)

# plt.show()

In [66]: plt.figure(figsize=(16,9))

sns.heatmap(globalwarming_df.corr(), annot = True)

plt.show()

In [67]: breast_cancer = pd.read_csv('breast_cancer.csv')

breast_cancer.drop('Unnamed: 32',axis = 1,inplace = True)

In [68]: breast_cancer.corr()

Out[68]: id radius_mean t ext ure_mean perimet er_mean area_mean smo

id 1.000000 0.074626 0.099770 0.073159 0.096893

radius_mean 0.074626 1.000000 0.323782 0.997855 0.987357

t ext ure_mean 0.099770 0.323782 1.000000 0.329533 0.321086

perimet er_mean 0.073159 0.997855 0.329533 1.000000 0.986507

area_mean 0.096893 0.987357 0.321086 0.986507 1.000000

smo o t hness_mean -0.012968 0.170581 -0.023389 0.207278 0.177028

co mpact ness_mean 0.000096 0.506124 0.236702 0.556936 0.498502

co ncavit y_mean 0.050080 0.676764 0.302418 0.716136 0.685983

co ncave po int s_mean 0.044158 0.822529 0.293464 0.850977 0.823269

symmet ry_mean -0.022114 0.147741 0.071401 0.183027 0.151293

f ract al_dimensio n_mean -0.052511 -0.311631 -0.076437 -0.261477 -0.283110

radius_se 0.143048 0.679090 0.275869 0.691765 0.732562

t ext ure_se -0.007526 -0.097317 0.386358 -0.086761 -0.066280

perimet er_se 0.137331 0.674172 0.281673 0.693135 0.726628

area_se 0.177742 0.735864 0.259845 0.744983 0.800086

smo o t hness_se 0.096781 -0.222600 0.006614 -0.202694 -0.166777

co mpact ness_se 0.033961 0.206000 0.191975 0.250744 0.212583

co ncavit y_se 0.055239 0.194204 0.143293 0.228082 0.207660

co ncave po int s_se 0.078768 0.376169 0.163851 0.407217 0.372320

symmet ry_se -0.017306 -0.104321 0.009127 -0.081629 -0.072497

f ract al_dimensio n_se 0.025725 -0.042641 0.054458 -0.005523 -0.019887

radius_wo rst 0.082405 0.969539 0.352573 0.969476 0.962746

t ext ure_wo rst 0.064720 0.297008 0.912045 0.303038 0.287489

perimet er_wo rst 0.079986 0.965137 0.358040 0.970387 0.959120

area_wo rst 0.107187 0.941082 0.343546 0.941550 0.959213

smo o t hness_wo rst 0.010338 0.119616 0.077503 0.150549 0.123523

co mpact ness_wo rst -0.002968 0.413463 0.277830 0.455774 0.390410

co ncavit y_wo rst 0.023203 0.526911 0.301025 0.563879 0.512606

co ncave po int s_wo rst 0.035174 0.744214 0.295316 0.771241 0.722017

symmet ry_wo rst -0.044224 0.163953 0.105008 0.189115 0.143570

f ract al_dimensio n_wo rst -0.029866 0.007066 0.119205 0.051019 0.003738

31 rows × 31 columns

In [89]: # plt.figure(figsize = (30,30))

# sns.heatmap(breast_cancer.corr(),annot = True,linewidths = 2)

# plt.show()

 Pairplot

In [77]: # sns.pairplot(breast_cancer)

# plt.show()

In [80]: # sns.pairplot(breast_cancer.corr())

# plt.show()

In [82]: breast_cancer.describe()

Out[82]: id radius_mean t ext ure_mean perimet er_mean area_mean smo o t hness_mea

co unt 5.690000e+02 569.000000 569.000000 569.000000 569.000000 569.00000

mean 3.037183e+07 14.127292 19.289649 91.969033 654.889104 0.09636

st d 1.250206e+08 3.524049 4.301036 24.298981 351.914129 0.01406

min 8.670000e+03 6.981000 9.710000 43.790000 143.500000 0.05263

25% 8.692180e+05 11.700000 16.170000 75.170000 420.300000 0.08637

50% 9.060240e+05 13.370000 18.840000 86.240000 551.100000 0.09587

75% 8.813129e+06 15.780000 21.800000 104.100000 782.700000 0.10530

max 9.113205e+08 28.110000 39.280000 188.500000 2501.000000 0.16340

8 rows × 31 columns

In [83]: featureMeans = list(breast_cancer.columns[1:11])

In [84]: correlationData = breast_cancer[featureMeans].corr()

sns.pairplot(breast_cancer[featureMeans].corr(),diag_kind = 'kde',size = 2)

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\axisgrid.py:2076: UserWarning: The `size` parameter has been re
named to `height`; please update your code.
warnings.warn(msg, UserWarning)
In [92]: plt.figure(figsize = (10,10))

sns.heatmap(breast_cancer[featureMeans].corr(),annot = True,square = True,cma

plt.show()

 CampusX
In [2]: import seaborn as sns

import matplotlib.pyplot as plt

import numpy as np

import pandas as pd

In [3]: plt.style.use('fivethirtyeight')

In [4]: tips_df = pd.read_csv('tips.csv')

tips_df.head()

Out[4]: t o t al_bill t ip sex smo ker day t ime size

0 16.99 1.01 Female No Sun Dinner 2

1 10.34 1.66 Male No Sun Dinner 3

2 21.01 3.50 Male No Sun Dinner 3

3 23.68 3.31 Male No Sun Dinner 2

4 24.59 3.61 Female No Sun Dinner 4

Scatter Plot

In [101… sns.regplot(x = 'total_bill',y = 'tip',data = tips_df)

plt.show()

In [103… sns.scatterplot(x = 'total_bill',y = 'tip',hue = 'smoker',data = tips_df)

plt.show()

In [107… sns.scatterplot(x = 'total_bill',y = 'tip',hue = 'smoker',style = 'sex',data

plt.show()

In [109… sns.scatterplot(x = 'total_bill',y = 'tip',hue = 'smoker',style = 'sex',size

plt.show()

Strip & Swarm Plot

In [110… sns.catplot(x = 'day',y = 'tip',kind = 'strip',data = tips_df)

plt.show()

In [115… sns.catplot(x = 'day',y = 'tip',kind = 'strip',jitter = 2,data = tips_df)

plt.show()

In [116… sns.catplot(x = 'day',y = 'tip',kind = 'strip',jitter = 0,data = tips_df)

plt.show()

In [117… sns.catplot(x = 'day',y = 'tip',kind = 'swarm',data = tips_df)

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\categorical.py:1296: UserWarning: 8.1% of the points cannot be
placed; you may want to decrease the size of the markers or use stripplot.
warnings.warn(msg, UserWarning)

In [118… sns.catplot(x = 'day',y = 'tip',kind = 'swarm',hue = 'sex',data = tips_df)

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\categorical.py:1296: UserWarning: 8.1% of the points cannot be
placed; you may want to decrease the size of the markers or use stripplot.
warnings.warn(msg, UserWarning)
In [119… # sns.swarmplot(x = 'day',y = 'tip',data = tips_df)

# plt.show()

Box Plot

In [5]: sns.boxplot(tips_df['tip'])

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable a
s a keyword arg: x. From version 0.12, the only valid positional argument wi
ll be `data`, and passing other arguments without an explicit keyword will r
esult in an error or misinterpretation.
warnings.warn(
In [6]: sns.boxplot(tips_df['total_bill'])

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable a
s a keyword arg: x. From version 0.12, the only valid positional argument wi
ll be `data`, and passing other arguments without an explicit keyword will r
esult in an error or misinterpretation.
warnings.warn(

In [7]: sns.catplot(x = 'day',y = 'total_bill',kind = 'box',data = tips_df)

plt.show()

In [8]: sns.catplot(x = 'day',y = 'total_bill',hue = 'sex',kind = 'box',data = tips_d

plt.show()

Violin Plot

In [9]: sns.violinplot(tips_df['total_bill'])

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable a
s a keyword arg: x. From version 0.12, the only valid positional argument wi
ll be `data`, and passing other arguments without an explicit keyword will r
esult in an error or misinterpretation.
warnings.warn(
In [10]: sns.catplot(x = 'day',y = 'total_bill',kind = 'violin',data = tips_df)

plt.show()

In [12]: sns.catplot(x = 'day',y = 'total_bill',kind = 'violin',hue = 'sex',split = Tr

plt.show()

 Bar & Count Plot

In [15]: sns.catplot(x = 'smoker',y = 'total_bill',kind = 'bar',data = tips_df)

plt.show()

In [16]: sns.catplot(x = 'smoker',y = 'total_bill',hue = 'sex',kind = 'bar',data = tip

plt.show()

In [17]: sns.catplot(x = 'smoker',y = 'total_bill',hue = 'sex',estimator = np.median,k

plt.show()

In [18]: sns.catplot(x = 'smoker',y = 'total_bill',hue = 'sex',estimator = np.var,kind

plt.show()

In [19]: sns.catplot(x = 'smoker',y = 'total_bill',hue = 'sex',estimator = np.std,kind

plt.show()

In [22]: sns.catplot(x = 'sex',kind = 'count',data = tips_df)

plt.show()

In [23]: sns.catplot(x = 'sex',hue = 'smoker',kind = 'count',data = tips_df)

plt.show()

Heatmap

In [33]: plt.style.use('fivethirtyeight')

In [34]: flights_df = pd.read_csv('flights.csv')

flights_df.head()

Out[34]: year mo nt h passengers

0 1949 January 112

1 1949 February 118

2 1949 March 132

3 1949 April 129

4 1949 May 121

In [35]: x = flights_df.pivot_table(index = 'year',columns = 'month',values = 'passeng

In [36]: # plt.figure(figsize = (10,10))

sns.heatmap(x)

plt.show()

In [37]: sns.heatmap(x,cbar = False)

plt.show()

In [40]: sns.heatmap(x,linewidths = 0.5,annot = True,fmt = 'd')

plt.show()

In [44]: sns.heatmap(x,linewidths = 0.5,annot = True,fmt = 'd',cmap = 'summer')

plt.show()

 Clustermap

In [45]: sns.clustermap(x)

plt.show()

In [48]: sns.clustermap(x,z_score = 0,annot = True,metric = 'correlation')

plt.show()

In [49]: sns.clustermap(x,z_score = 0,annot = True,row_cluster = False,metric = 'corre

plt.show()

In [50]: sns.clustermap(x,z_score = 0,annot = True,col_cluster = False,metric = 'corre

plt.show()

 Joint Plot

In [51]: sns.jointplot(x = 'total_bill',y = 'tip',data = tips_df)

plt.show()

In [52]: sns.jointplot(x = 'total_bill',y = 'tip',kind = 'hex',data = tips_df)

plt.show()

In [57]: sns.jointplot(x = 'total_bill',y = 'tip',kind = 'kde',data = tips_df)

plt.show()

In [59]: sns.jointplot(x = 'total_bill',y = 'tip',kind = 'reg',data = tips_df)

plt.show()

In [60]: sns.jointplot(x = 'total_bill',y = 'tip',kind = 'resid',data = tips_df)

plt.show()

 Pair Plot

In [63]: plt.style.use('fivethirtyeight')

In [64]: iris_df = pd.read_csv('iris.csv')

iris_df.head()

Out[64]: sepal_lengt h sepal_widt h pet al_lengt h pet al_widt h species

0 5.1 3.5 1.4 0.2 setosa

1 4.9 3.0 1.4 0.2 setosa

2 4.7 3.2 1.3 0.2 setosa

3 4.6 3.1 1.5 0.2 setosa

4 5.0 3.6 1.4 0.2 setosa

In [65]: sns.pairplot(iris_df)

plt.show()

In [66]: sns.pairplot(iris_df,hue = 'species')

plt.show()

 Dist Plot

In [68]: plt.style.use('fivethirtyeight')

In [69]: titanic_df = pd.read_csv('titanic.csv')

titanic_df.head()

Out[69]: survived pclass sex age sibsp parch f are embarked class who adult _male de

0 0 3 male 22.0 1 0 7.2500 S T hird man T rue N

1 1 1 female 38.0 1 0 71.2833 C First woman False

2 1 3 female 26.0 0 0 7.9250 S T hird woman False N

3 1 1 female 35.0 1 0 53.1000 S First woman False

4 0 3 male 35.0 0 0 8.0500 S T hird man T rue N

In [70]: titanic_df['age'].fillna(titanic_df['age'].mean(),inplace = True)

In [76]: sns.distplot(titanic_df['age'])

plt.show()

In [74]: sns.distplot(titanic_df['age'],kde = False)

plt.show()

In [75]: sns.distplot(titanic_df['age'],bins = 10,kde = False)

plt.show()

In [81]: sns.distplot(titanic_df['age'],hist = False)

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`kdeplot` (an axes-level function for kernel density plots).
warnings.warn(msg, FutureWarning)

In [83]: sns.distplot(titanic_df['age'],hist = False,kde = False,rug = True)

plt.show()

 C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2103: FutureWarning: The `axis` variable is no
longer used and will be removed. Instead, assign variables directly to `x` o
r `y`.
warnings.warn(msg, FutureWarning)

In [85]: sns.distplot(titanic_df[titanic_df['survived']==1]['age'])

sns.distplot(titanic_df[titanic_df['survived']==0]['age'])

plt.show()

C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
C:\Users\prasad jadhav\AppData\Local\Programs\Python\Python310\lib\site-pack
ages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecate
d function and will be removed in a future version. Please adapt your code t
o use either `displot` (a figure-level function with similar flexibility) or
`histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
Thank You