Matplotlib

In [1]: import numpy as np

import pandas as pd
import matplotlib
from matplotlib import pyplot as plt

/Users/satyakumarpalli/anaconda3/lib/python3.10/site-packages/pandas/core/arrays/masked.py:60: UserWarning: Pandas requires version '1.3.6' or newer of 'bottleneck' (ve

rsion '1.3.5' currently installed).
from pandas.core import (

Line Plot
In [2]: a = np.array([1,2,3,4,5,6,7,8])

In [3]: plt.plot(a)

Out[3]: [<matplotlib.lines.Line2D at 0x14acb3dc0>]

In [4]: a = np.array([1,2,3,4])
b = np.array([10,20,30,40])
plt.plot(a,b)

Out[4]: [<matplotlib.lines.Line2D at 0x14adeadd0>]

In [5]: a = np.array([1,2,3,4])
b = np.array([10,20,30,40])
plt.plot(a,b,'r')

Out[5]: [<matplotlib.lines.Line2D at 0x14af7d240>]

'r'. - red 'g'. - green 'b'. - blue 'c'. - cyan 'm'. - megenta 'y'. - yellow 'w'. - white 'k'. - black
In [6]: a = np.array([1,2,3,4])
b = np.array([10,20,30,40])
plt.plot(a,b,'red')

Out[6]: [<matplotlib.lines.Line2D at 0x14afeb7c0>]

In [7]: a = np.array([1,2,3,4])
b = np.array([10,20,30,40])
plt.plot(a,b,'green')

Out[7]: [<matplotlib.lines.Line2D at 0x14b072110>]

In [8]: x = np.linspace(1,100,1000)
y = np.sin(x)
plt.plot(x,y,'m')
plt.show()

In [9]: x = np.linspace(1,100,1000)
y = np.sin(x)
plt.plot(x,y,'m')
plt.xlabel('Time')
plt.ylabel('Amplitude')
plt.show()

In [10]: plt.figure(figsize=(8,3)) #size = width,hight

x = np.linspace(1,100,1000)
y = np.sin(x)
plt.plot(x,y,'m')
plt.xlabel('Time')
plt.ylabel('Amplitude')
plt.show()

In [11]: plt.figure(figsize=(8,3)) #size = width,hight

x = np.linspace(1,100,1000)
y = np.sin(x)
plt.plot(x,y,'g')
plt.xlabel('Time')
plt.ylabel('Amplitude')
plt.grid()
plt.show()

In [12]: plt.figure(figsize=(8,3)) #size = width,hight

x = np.linspace(1,100,1000)
y = np.sin(x)
plt.plot(x,y,'g')
plt.xlabel('Time')
plt.ylabel('Amplitude')
plt.title('Sinewave')
plt.grid()
plt.show()

In [13]: plt.figure(figsize=(4,3))
a = np.array([10,45,23,67,12])
plt.plot(a,'b')
plt.show()

In [14]: plt.figure(figsize=(4,3))
a = np.array([10,45,23,67,12])
plt.plot(a,'r:*')
plt.show()

In [15]: plt.figure(figsize=(8,3)) #size = width,hight

x = np.linspace(1,100,1000)
y = np.sin(x)
plt.plot(x,y,'b:')
plt.xlabel('Time')
plt.ylabel('Amplitude')
plt.title('Sinewave')
plt.grid()
plt.show()

Line Reference 1. '-' solid line 2. ':' Dotted line 3. '--' dashed line 4. '-.' dash dot line
Marker reference 'o' circle '*' star '.' point 'x' X 'X' X(filled) '+' Plus 'P' Plus(filled) 's' Square 'D' Dimond 'v' Traiangle down '^' traingle up '<' traingle left '>' traingle right
In [16]: plt.figure(figsize=(4,3))
a = np.array([10,45,23,67,12])
plt.plot(a,'r:*')
plt.show()

In [17]: plt.figure(figsize=(4,3))
a = np.array([10,45,23,67,12])
plt.plot(a,'b-.P')
plt.show()

In [18]: plt.figure(figsize=(4,3))
a = np.array([10,45,23,67,12])
plt.plot(a,marker='D',mfc='r',mec='b')
plt.show()

In [19]: plt.figure(figsize=(4,3))
a = np.array([10,45,23,67,12])
plt.plot(a,marker='D',ms=10,mfc='r',mec='b')
plt.show()

In [20]: plt.figure(figsize=(4,3))
a = np.array([10,45,23,67,12])
plt.plot(a,color='y',marker='D',ms=10,mfc='r',mec='k')
plt.show()

In [21]: #plot multiple line plots in single figure window

In [22]: plt.figure(figsize=(8,4)) #size = width,hight

x = np.linspace(0,10,1000)
y = np.sin(x)
z = np.cos(x)
plt.plot(x,y,'g-',label='sinewave')
plt.plot(x,z,'r-',label='cosine wave')
plt.xlabel('Time')
plt.ylabel('Amplitude')
plt.title('Sinewave')
plt.grid()
plt.legend(loc='upper right')
plt.show()

subplots
In [23]: plt.figure(figsize=(6,3))
x = np.linspace(0,10,1000)
y = np.sin(x)
plt.subplot(1,2,1)
plt.plot(x,y,'r')
plt.grid()
z = np.cos(x)
plt.subplot(1,2,2)
plt.plot(x,z,'g')
plt.grid()

In [24]: plt.figure(figsize=(6,3))
x = np.linspace(0,10,1000)
y = np.sin(x)

plt.subplot(2,2,1)
plt.plot(x,y,'r')
plt.grid()

z = np.cos(x)
plt.subplot(2,2,2)
plt.plot(x,z,'g')
plt.grid()

plt.subplot(2,2,3)
plt.plot(x-20,y,'y')
plt.grid()

plt.subplot(2,2,4)
plt.plot(x-40,y,'m')
plt.grid()

In [25]: plt.figure(figsize=(6,3)) #size = width,hight

x = np.linspace(0,10,1000)
y = np.sin(x)
plt.plot(x,y,color='#76d7c4',linewidth=4)
plt.xlabel('Time')
plt.ylabel('Amplitude')
plt.title('Sinewave')
plt.grid()
plt.show()

Bar plot
In [ ]:

In [26]: a =['satya','sekhar','jayanth','Vishnu']
b =[25,50,75,90]
plt.figure(figsize=(6,3)) #size = width,hight
plt.bar(a,b)
plt.show()

In [27]: a =['satya','sekhar','jayanth','Vishnu']
b =[25,50,75,90]
plt.figure(figsize=(6,3)) #size = width,hight
plt.bar(a,b,color='m')
plt.show()

In [28]: a =['satya','sekhar','jayanth','Vishnu']
b =[25,50,75,90]
plt.figure(figsize=(6,3)) #size = width,hight
plt.bar(a,b,color='m',width=0.4)
plt.show()

In [29]: a =['satya','sekhar','jayanth','Vishnu']
b =[25,50,75,90]
plt.figure(figsize=(6,3)) #size = width,hight
plt.barh(a,b)
plt.show()

In [30]: df = pd.read_csv('cleaned_titanic.csv')

In [31]: df.drop('Unnamed: 0',axis='columns',inplace=True)

df

Out[31]: survived pclass sex age sibsp parch fare embarked class who adult_male embark_town alive alone

0 0 3 male 22.000000 1 0 7.2500 S Third man True Southampton no False

1 1 1 female 38.000000 1 0 71.2833 C First woman False Cherbourg yes False

2 1 3 female 26.000000 0 0 7.9250 S Third woman False Southampton yes True

3 1 1 female 35.000000 1 0 53.1000 S First woman False Southampton yes False

4 0 3 male 35.000000 0 0 8.0500 S Third man True Southampton no True

... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

886 0 2 male 27.000000 0 0 13.0000 S Second man True Southampton no True

887 1 1 female 19.000000 0 0 30.0000 S First woman False Southampton yes True

888 0 3 female 29.699118 1 2 23.4500 S Third woman False Southampton no False

889 1 1 male 26.000000 0 0 30.0000 C First man True Cherbourg yes True

890 0 3 male 32.000000 0 0 7.7500 Q Third man True Queenstown no True

891 rows × 14 columns

In [41]: plt.figure(figsize=(4,2))
df['sex'].value_counts().plot(kind='bar',color = 'r',width=0.2)

Out[41]: <Axes: xlabel='sex'>

In [42]: #plot a bar plot to show how many mem, women and child passengers were onboarded into ship?

In [44]: plt.figure(figsize=(4,2))
df['who'].value_counts().plot(kind='bar',color = 'm',width=0.2)

Out[44]: <Axes: xlabel='who'>

In [45]: #plot a bar graph to show how many females are survived and not survived

In [54]: df[df['sex']=='female'].groupby('survived')['sex'].count().plot(kind='bar',color='y')

Out[54]: <Axes: xlabel='survived'>

In [57]: df[df['sex']=='female'].groupby('survived')['sex'].count().plot(kind='bar',color='c')

Out[57]: <Axes: xlabel='survived'>

In [58]: #plot a bar graph to show how many passengers from third class were alive and how many were
#not alive

In [60]: df[df['class']=='Third'].groupby('alive')['class'].count().plot(kind='bar',color='m')

Out[60]: <Axes: xlabel='alive'>

In [61]: #plot a bar graph to show how many adultmale passengers embark town was southampton and
# and queenstown

In [65]: df[df['embark_town'].isin(['Southampton','Queenstown'])].groupby('embark_town')['adult_male'].count()

Out[65]: embark_town
Queenstown 77
Southampton 646
Name: adult_male, dtype: int64

In [81]: plt.figure(figsize=(4,2))
df[df['adult_male']==True].groupby('embark_town')['adult_male'].count()[1:].plot(kind='bar')

Out[81]: <Axes: xlabel='embark_town'>

In [ ]: df[df['adult_male']==True]

In [76]: df[df['adult_male']==True][(df['embark_town']=='Southampton')|(df['embark_town']=='Queenstown')]['embark_town'].value_counts().plot(kind='bar')

/var/folders/nn/9bkkh7612wg2c3gglt0zd9h40000gn/T/ipykernel_81114/711970834.py:1: UserWarning: Boolean Series key will be reindexed to match DataFrame index.
df[df['adult_male']==True][(df['embark_town']=='Southampton')|(df['embark_town']=='Queenstown')]['embark_town'].value_counts().plot(kind='bar')
Out[76]: <Axes: xlabel='embark_town'>

sctter plot
In [82]: #plt.scatter()

In [85]: plt.figure(figsize=(4,4))
a = np.array([34,56,78,90,12,34,52])
b = np.array([45,67,89,23,90,45,12])
plt.scatter(a,b)
plt.show()

In [86]: a = np.random.randint(1,100,30)

In [89]: b = np.random.randint(10,100,30)

plt.scatter(a,b,color = 'hotpink')
plt.show()

In [90]: a = np.random.randint(1,100,30)
b = np.random.randint(10,100,30)

c = np.random.randint(1,100,20)
d = np.random.randint(10,100,20)

plt.scatter(a,b,color = 'hotpink')
plt.scatter(c,d,color='yellowgreen')
plt.show()

In [117… a = np.random.randint(1,100,10)
b = np.random.randint(10,100,10)
cols = ['red','green','blue','cyan','magenta','yellow','hotpink','yellowgreen','brown','red']
plt.scatter(a,b,color = cols)

Out[117]: <matplotlib.collections.PathCollection at 0x166b79930>

In [107… a

Out[107]: array([22, 1, 25, 60, 22, 31, 78, 55, 41, 44])

In [108… b

Out[108]: array([71, 26, 15, 33, 76, 11, 44, 65, 35, 62])

In [109… C

Out[109]: array(['red', 'green', 'blue', 'cyan', 'megenta', 'yellow', 'hotpink',

'yellowgreen', 'brown', 'red'], dtype='<U11')

In [115… a = np.array([10,20,34,56,67,78,89])
b = np.array([20,30,45,12,35,46,67])
colors = np.array(["red","blue","m",'cyan',"brown","black","green"])
plt.scatter(a,b,c=colors)

Out[115]: <matplotlib.collections.PathCollection at 0x1669eab60>

In [119… a = np.array([10,20,34,56,67,78,89])
b = np.array([20,30,45,12,35,46,67])
colors = np.array(["red","blue","m",'cyan',"brown","black","green"])
sizes = np.array([10,20,30,40,50,60,70])
plt.scatter(a,b,c=colors,s=sizes)
plt.show()

In [125… a = np.array([10,20,34,56,67,78,89])
b = np.array([20,30,45,12,35,46,67])
colors = np.array(["red","blue","m",'cyan',"brown","black","green"])
sizes = np.array([10,20,30,40,50,60,70])
plt.scatter(a,b,c=colors,s=sizes,alpha=0.5)
plt.show()

In [129… #plot a scatter plot for two array variable containig 100 random numbers in each with
#transperancy 0.7
a = np.random.random(100)
b = np.random.random(100)
plt.scatter(a,b,color = 'red',alpha=0.4)
plt.show()

Pie Charts
In [131… a = np.array([25,23,42,10])
plt.pie(a)
plt.show()

In [132… a = np.array([25,23,42,10])
L = np.array(['Ecommerce','Dining','Clothing','Online'])
plt.pie(a,labels=L)
plt.show()

In [133… a = np.array([25,23,42,10])
L = np.array(['Ecommerce','Dining','Clothing','Online'])
plt.pie(a,labels=L,startangle = 90)
plt.show()

In [137… a = np.array([25,23,42,10])
L = np.array(['Ecommerce','Dining','Clothing','Online'])
plt.pie(a,labels=L,startangle = 90,explode = [0,0.09,0,0])
plt.show()

In [138… a = np.array([25,23,42,10])
L = np.array(['Ecommerce','Dining','Clothing','Online'])
plt.pie(a,labels=L,startangle = 90,explode = [0,0.09,0,0],shadow=True)
plt.show()

In [140… a = np.array([25,23,42,10])
L = np.array(['Ecommerce','Dining','Clothing','Online'])
C =np.array(['hotpink','yellowgreen','brown','green'])
plt.pie(a,labels=L,startangle = 90,colors = C, explode = [0,0.09,0,0],shadow=True)
plt.show()

In [142… a = np.array([25,23,42,10])
L = np.array(['Ecommerce','Dining','Clothing','Online'])
C =np.array(['hotpink','yellowgreen','brown','green'])
plt.pie(a,labels=L,startangle = 90,colors = C, explode = [0,0.09,0,0],shadow=True)
plt.legend(loc='upper right')
plt.show()

In [143… a = np.array([25,23,42,10])
L = np.array(['Ecommerce','Dining','Clothing','Online'])
C =np.array(['hotpink','yellowgreen','brown','green'])
plt.pie(a,labels=L,startangle = 90,colors = C, explode = [0,0.09,0,0],shadow=True)
plt.legend(loc='upper right',title='Spend Analysis')
plt.show()

In [147… a = np.array([25,23,42,10])
L = np.array(['Ecommerce','Dining','Clothing','Online'])
C =np.array(['hotpink','yellowgreen','brown','green'])
plt.pie(a,labels=L,startangle = 90,colors = C, explode = [0,0.09,0,0],shadow=True,autopct='%1.2f%%')
plt.legend(loc='upper right',title='Spend Analysis')
plt.show()

In [148… df

Out[148]: survived pclass sex age sibsp parch fare embarked class who adult_male embark_town alive alone

0 0 3 male 22.000000 1 0 7.2500 S Third man True Southampton no False

1 1 1 female 38.000000 1 0 71.2833 C First woman False Cherbourg yes False

2 1 3 female 26.000000 0 0 7.9250 S Third woman False Southampton yes True

3 1 1 female 35.000000 1 0 53.1000 S First woman False Southampton yes False

4 0 3 male 35.000000 0 0 8.0500 S Third man True Southampton no True

... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

886 0 2 male 27.000000 0 0 13.0000 S Second man True Southampton no True

887 1 1 female 19.000000 0 0 30.0000 S First woman False Southampton yes True

888 0 3 female 29.699118 1 2 23.4500 S Third woman False Southampton no False

889 1 1 male 26.000000 0 0 30.0000 C First man True Cherbourg yes True

890 0 3 male 32.000000 0 0 7.7500 Q Third man True Queenstown no True

891 rows × 14 columns

In [149… #plot pie chart for showing percentage of passengers who boarded in first, second , third
# class in titanic

In [155… df['class'].value_counts().plot(kind='pie',autopct='%1.2f%%')

Out[155]: <Axes: ylabel='count'>

In [153… df['class'].value_counts()

Out[153]: class
Third 491
First 216
Second 184
Name: count, dtype: int64

In [160… #plot a pie chart for showing percentages of people in age group 19 -23, 23 to 35, 35 - max
ages = df['age'].astype(int)

In [180… ages[ages>19].count()

Out[180]: 727

In [182… ages[ages>35].count()

Out[182]: 217

In [185… ages[ages<35].count()

Out[185]: 656

In [214… ag1 = df[(df['age']>19) & (df['age']<23)]

In [204… ag2 = df[(df['age']>23) & (df['age']<35)]

ag3 = df[(df['age']>35) ]

In [216… ag1 = ag1['age'].count()

ag2 = ag2['age'].count()
ag3 = ag3['age'].count()

In [221… plt.pie([ag1,ag2,ag3],labels= ['age group-1','age Group-2','age Group-3'],autopct='%1.2f%%')

plt.legend()
plt.show()

Histogram
In [222… a = np.random.randn(1000)

In [226… plt.hist(a,bins=10, color='lightgreen',edgecolor='blue')

plt.show()

In [227… ages = np.array([12,13,45,67,89,76,54,32,23,24,25,26,76,67,56,57,46,30,82,31,90,20,34,12,9,10])

In [239… plt.hist(ages,bins =20,color='skyblue',edgecolor='red')

plt.show()

In [237… df['age'].astype(int).plot(kind='hist',color = 'lightgreen',bins=20,edgecolor='red')

Out[237]: <Axes: ylabel='Frequency'>

In [240… #plot an of of 10000 random values in 10 bins with edgecolor blue and bar color yellowgreen

In [242… a = np.random.random(10000)
plt.hist(a, color = 'yellowgreen',edgecolor = 'blue')
plt.show()

In [246… # plot histogram or fare in titanic dataset with 10 bins

In [249… df['fare'].plot(kind='hist',bins=10,color='brown',edgecolor='yellowgreen')
plt.show()

In [251… #plot histogram for age in titanic dataset

df['age'].plot(kind='hist',bins=20,color='lightgreen',edgecolor='red')
plt.show()

area plots
In [252… a = np.array([10,20,30,40,50])
b = np.array([5,10,15,20,25])

In [253… plt.plot(a,b)
plt.fill_between(a,b)
plt.show()

In [257… x = np.linspace(1,10,1000)
y = np.sin(x)
plt.plot(x,y)
plt.fill_between(x,y,color='red')
plt.show()

In [258… df1 = pd.DataFrame({'ID':[101,102,103,104,105],'Marks':[98,99,89,76,57]})

In [259… df1

Out[259]: ID Marks

0 101 98

1 102 99

2 103 89

3 104 76

4 105 57

In [260… df2 = pd.DataFrame({'ID':[101,102,105,106,107],'Marks':[89,67,34,56,90]})

In [261… df2

Out[261]: ID Marks

0 101 89

1 102 67

2 105 34

3 106 56

4 107 90

In [262… #inner join

In [264… out = pd.merge(df1,df2,on = 'ID',how='inner')

In [265… out

Out[265]: ID Marks_x Marks_y

0 101 98 89

1 102 99 67

2 105 57 34

In [266… out2 = pd.merge(df1,df2,on = 'ID',how='outer')

In [267… out2

Out[267]: ID Marks_x Marks_y

0 101 98.0 89.0

1 102 99.0 67.0

2 103 89.0 NaN

3 104 76.0 NaN

4 105 57.0 34.0

5 106 NaN 56.0

6 107 NaN 90.0

In [268… out3 = pd.merge(df1,df2,on='ID',how='left')

In [269… out3

Out[269]: ID Marks_x Marks_y

0 101 98 89.0

1 102 99 67.0

2 103 89 NaN

3 104 76 NaN

4 105 57 34.0

In [270… out4 = pd.merge(df1,df2,on='ID',how='right')

out4

Out[270]: ID Marks_x Marks_y

0 101 98.0 89

1 102 99.0 67

2 105 57.0 34

3 106 NaN 56

4 107 NaN 90

In [ ]: