Scribd
Upload
92 views31 pages

Matplotlib Fundamentals

Uploaded by

Shubham Vishwakarma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
92 views31 pages

Matplotlib Fundamentals

Uploaded by

Shubham Vishwakarma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 31
‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [1]: #Importing Libraries import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns 2D- e Plot In [3]: # Bivariate Analysis # For Categorical -Numerical and Numerical- Numerical, # It is plot on Time series data. In [2]: tpLoting a simple graph price= [55000,49000, 62000, 50000] year= [2015,2016,2017, 2018] fplt. plot (x-axis, y-axis) plt.plot(year, price) plt.grid() plt.show() ‘2000 0000 58000 56000, 54000 52000 50000 2150 2155 20160 20165 2170 2175 2180 locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb at ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [7] #PLotting by Loading a dataset Batsman= pd.read_csv("sharma-kohli.csv") Batsman.head() out[7]: Index RG Sharma V Kohli © 2008 404165 1 2008 362246, 2 2010 404307 3 2011 372887 4 2012 433364 In [16]: plt.plot(Batsman[ "index" ],Batsman["V Kohli"]) out [10]: [] 1000 so 800 700 «00 s00 400 300 200 2008 2010 iz 2014 216 locathost 8888/notebooks!ard Semester/My Practce/MatplotiiyMatpotibjpynb 261 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In (11): #Ploting multiple graphs plt.plot(Batsman[ "index" ],B8atsman{"V Kohli"]) plt. plot (Batsman[ "index" ],Batsman["RG Sharma"]) out[11]: [] 1000 so 800 700 «00 s00 400 300 200 72008 2010 iz 2014 216 In [14]: a#Ploting with title plt.plot(Batsman["index"],Batsman["V Kohli"]) plt.plot(Batsman[ "index" ],Batsman["RG Sharma”]) plt.title("Rohit Sharma V/S Virat Kohli plt.xlabel("Season") plt.ylabel("Runs Scored") out [14]: Text(0, 0.5, ‘Runs Scored") Rohit Sharma W/S Virat Kohli 3000 00 00 700 00 500 Runs Scored 400 300 200 2008 2010 2012 2014 2016 ‘Season locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 301 187128, 11:27 PM Matploil-Jupyter Notebook In [15]: # Changing the colour (hex color) plt.plot(Batsman["index"],Batsman["V Kohli"], color="green") plt.plot(Batsman["index"],Batsman["RG Sharma], color="blue") plt.title("Rohit Sharma V/S Virat Kohli pit.xlabel("Season") plt.ylabel("Runs Scored") out [15]: Text(®, 8.5, ‘Runs Scored") Rohit Sharma /S Virat Kohli 3000 09 00 709 «00 500 Runs Scored 300 200 2008 2010 2012 214 2016 ‘Season localhost 8888 /notebooks/3rd Semester/My Practce/MatpotibyMatpotibipyno 401 187128, 11:27 PM Matploil-Jupyter Notebook In [16]: # Other than solid Line(dashed, dotted, dashdot) plt.plot(Batsman["index"],Batsman["V Kohli"], colo plt.plot(Batsman["index"],Batsman["RG Sharma"], colo reen", Linestyle="dashed") blue", linestyle="dashed”) plt.title("Rohit Sharma V/S Virat Kohli plt.xlabel("Season") plt.ylabel("Runs Scored") out [16]: Text(®, 8.5, ‘Runs Scored’) Rohit Sharma /S Virat Kohli Runs Scored 2008 2010 2012 214 2016 locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 501 187128, 11:27 PM Matploil-Jupyter Notebook In [26]: # Line width plt.plot(Batsman["index" ],Batsman["V Kohli"], color="green", linestyle="solid", Linewidt plt.plot(Batsman["index"],Batsman["RG Sharma], color="blue", linestyle="dashed", linewi, plt.title("Rohit Sharma V/S Virat Kohli pit.xlabel("Season") plt.ylabel("Runs Scored") out [20]: Text(®, 0.5, ‘Runs Scored") Rohit Sharma /S Virat Kohli 3000 Runs Scored locathost 8888/notebooks!ard Semester/My Practce/MatplotiiyMatpotibjpynb 301 187128, 11:27 PM Matploil-Jupyter Notebook In [28]: # Marker plt.plot(Batsman["index"],Batsman["V Kohli], color="green", marker=".", markersize=10 ) plt.plot(Batsman["index"],Batsman["RG Sharma"), color="blue", linestyle="dashed”) plt.title("Rohit Sharma V/S Virat Kohli plt.xlabel("Season") plt.ylabel("Runs Scored") out [28]: Text(®, 8.5, ‘Runs Scored") Rohit Sharma /S Virat Kohli 3000 Runs Scored localhost 8888 /notebooks/3rd Semester/My Practce/MatpotibyMatpotibipyno 781 187128, 11:27 PM Matploil-Jupyter Notebook In [30]: # Using Lagend plt.plot(Batsman["index"],Batsman["V Kohli"], colo plt.plot(Batsman["index"],Batsman["RG Sharma"], colo ren", labe blue" , labe: plt.title("Rohit Sharma V/S Virat Kohli plt.xlabel("Season") plt.ylabel("Runs Scored") plt.legend() Out [3@]: _______Rohit Sharma V/S Virat Kohli — Wat 900 | — Rohit 3000 200 700 600 Runs Scored 500 400 300 200 2008 2010 2012 2014 2016 ‘Season locathost 8888/notebooks!ard Semester/My Practce/MatplotiiyMatpotibjpynb 31 187128, 11:27 PM Matploil-Jupyter Notebook In [31]: # Limiting axes (Mainly used for outliers) #(Bcoz of outliers graps can get flat or not accurate, we can trim for this type) price= [55000,49000, 62000, 500@000] year= [2015,2016,2017, 2018] dipLt. plot (x-axis, y-axis) plt.plot(year,price) pit. show() 2150 20155 2160 2165 2170 2175 20180 [55000,49000, 62000, Se00e0] (2015, 2016, 2017, 2018] dplt. plot (x-axis, y-axis) plt.plot(year, price) plt.ylim(0, 100000) plt.show() 300000 0000 2000 0000 20000 ° 2150 20155 2160 2165 2170 20175 20180 locathost 8888/notebooks!ard Semester/My Practce/MatplotiiyMatpotibjpynb 931 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [33]: price= [55000,49000, 62000, 5000000] year= [2615,2016,2017,2618] tpLt. plot (x-axis, y-axis) plt.plot(year,price) plt.ylim(9, 100000) plt.xlim(2016, 218) plt.show() 300000 0000 2000 40000 2000 ° 2016 002016 25 2016,502016 752017 002017 25 2017 502017.75 2018.00 In [34]: # Grid plt.plot(Batsman["index"],Batsman["V Kohli"], color="green", label= plt.plot(Batsman["index"],Batsman["RG Sharma"), color="blue" , labe plt.title("Rohit Sharma V/S Virat Kohli") plt.xlabel ("Season") plt.ylabel("Runs Scored") plt.legend() plt.grid() Rohit Sharma V/S Virat Kohli 3000 — Wat 200 | — Rohit 200 700 600 500 Runs Scored 400 300 200 2008 2010 2012 2014 2016 ‘Season locathost 8888/notebooks!ard Semester/My Practce/MatplotiiyMatpotibjpynb 10831 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook Scatter Plot In [3] import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns In [4]: # Bivariate Analysis # Numerical -Numerical # Finding Correlation between two quantities # (2d plot is the main output of scatter plot) In [5]: # Plotting simple scatter plot x= np.1inspace(-10, 10,5) x y= 10% +3+np. random. randint (0,300, 50) y plt.scatter(x,y) out[5]: 300 ° . Bo . o 200 150 100 00 75 50 25 00 25 so 75 100 locathost 8888/notebooks!ard Semester/My Practce/MatplotiiyMatpotibjpynb m1 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [6] wScatter plot on pandas dataframe Data= pd.read_csv("batter.csv") df= Data.head(5@) df locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 1281 7187129, 11:27 PM out[s]: batter ° V Koh 1 SDhawan 2 DAWamer 3 R@Sharma 4 SKRaina 5 AB4e Villers 6 CHGayle 7 MS Dhoni 8 RVUthappa 9 KO Karthik 40 GGambhir 11 ATRayudu 42 AMRahane 43° KLRehul 14 SRWatson 15 MK Pandey 46 SVSamson 47 KAPolard 18 F duPlessis 49 YK Pathan 20 BB McCullum 21 RRPant 22 ——~PAPatel 23 sc Butter 4 8S ler 25 QdeKock 26 Yuvraj Singh 27 VSehwag 28 SAYadav 2 MViay 30 RAJadeja 31 SPD Smith 32 SEMarsh 33 AMiler 34 JH Kallis 35 WPSaha 36 DRSmith 6634 e244 5983 5281 5536 5181 4907 4078 4954 477 a2t7 4190 407s 3895 3880 3657 3526 2437 3403 3222 2082 2251 2ada 2232 2780 2767 2754 27128 2644 2619 2502 2498 2489 2485 2427 2azr 2385 ag 36.251966 34.982682 44.42987 30314433, 32374269 so.esse46 39658730 9.196860 27522222 26852761 31.007353, 28,896552 30,863636 aor 30.793651 29.731707 29.140496 20.404959, aaarara7 29.290909 27.711598 4.768293, 2.603175, 39.399933, 31.236955, 31.204598 2410811 27555556, 29707865 25.930693, 2.617021 34,652778 39.507937 36.102041 28.552041 25281250 28.392867 strike_rate 125977972 122.4082 13640157 126.964504 132.595312 148 580842 142.121729 130.931089 126,152279 120.267572 119,665153 124,148148 197.575758 132.799182 134.169209, 117.739858 132.407060 140.457703, s27.167414 138,088272 126.a4a592 142.550000 116625717 144.259035, 121.192898 130951254 124.784776 148.827059 134009123, 118.614130 122,108346, 124,812808, 130,109775 133,569097 105.936272 124,397745, 132.279534 Maiplotity - Jupyter Notebook localhost 8888 /notebooks/3rd Semester/My Practce/MatpotibyMatpotibipyn 13931 7187129, 11:27 PM batter 37 MAAgarwal 38 SR Tendulkar 39 GJ Maxwell 40 NRana a R Dravid 42. KS Williamson “a AJ Finch 44 AC Gilchrist 45 AD Russell 46 JP Duminy 47 MEK Hussey 48 HH Pandya Up [73hubman Gil runs 2335, 2334 2320 2181 2174 2105 2092 2089 2039 2029 1977 1972 1900 plt.scatter(d#["avg out[7]: avg 2.669903 3.826087 25.494505 27.961538 28.233766 36.293103 24,904762 27.223684 29.985294 39,784314 8.764706 29.878788 2.203390 ,d#["strike_rate"]) strike_rate 129.506378 114187867 147.676639 130.053667 113347237 123.315759 123.349057 133.054662 168.234323 120.773610 119,963592 140.256046 122.186495 Maiplotity - Jupyter Notebook x70 ai 160 150 0 . uo . wofe . 0 oe uo . % 30 3 «0 6 localhost 8888 /notebooks/3rd Semester/My Practce/MatpotibyMatpotibipyno 14st ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [8]: # Labeling plt.scatter(df[ "avg" ],df["strike_rate"]) plt.xlabel ("Average") plt.ylabel("Strike_rate") plt.show() 70 a 160 150 AO ‘ # uo ° g . ° RB} . . 20 . . no : z ” s o & nverage In [9] # Labeling plt.scatter(df[ "avg" ],df["strike_rate"]) plt-xlabel("Average") plt.ylabel("Strike_rate") pit.show() o Buel s wo uo locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 1531 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In (16): Using Marker plt.scatter(df["avg"],df["strike_rate"], marker= plt.xlabel ("Average") plt.ylabel("Strike_rate") plt.show() 70 160 ‘Strike_rate In [11]: # Legend- Location od Legend plt.scatter(df["avg"],df["strike_rate"], label="average") plt-xlabel ("Average") plt.ylabel("Strike_rate") plt.legend(loc="upper left") pit. show() 170 emerge 160 180 Eso g 0 FB} . 0 . uo : B 2 s 0 5 locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 16131 ‘HR, 11:27 PM In wSize- LOADING A DATASET [22]: tips= sns.load_dataset("tips") tips out[12]: 239 240 2a 2a 243 total_bill 16.99 10.34 21.01 23.68 2459 2003 27.18 281 17.82 18.78 tip 401 1.66 3.50 331 361 5.92 2.00 2.00 475 3.00 Female Malo Malo Malo Female Male Female Male Male Female 244 rows * 7 columns In [13]: plt.scatter(tips["total_bill"], tips["tip"]) out[13]: smoker No No No No No No Yes Yes No No aay Sun sun sun sun sun sat sat Sat Sat Thur time Dinner Dinner Dinner Dinner Dinner Dinner Dinner Dinner Dinner Dinner Maiplotity - Jupyter Notebook » 10 locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb a3 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [14]: # Size will give us the number of person the customer came with plt.scatter(tips["total_bill"],tips["tip"], s=tips["size"]) out [14]: » ji 8 6 4 2 Fd » » a 50 In [15]: # Multiplying it by 2@ to increase the size of the plots plt.scatter(tips[“total_bill"],tips[“tip"], plt.xlabel("Total_bi11") plt.ylabel("Tips") =tips["size"]*26) out[15]: Text(@, 0.5, ‘Tips') 10 e locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 1831 187128, 11:27 PM Maiplotib-Jupyter Notebook In [16]: plt.plot(tips{"total_bill"],tips["tip"]) out [16]: [] » In [17]: #Faster technique to plot scatter plot plt.plot(tips["total_bill"],tips["tip"],"o" ) out[17}: [] » ° In [18]: # Note- we should not use plt.plot with "o" bcoz there are many parameters we can not us locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 19931 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook Bar Plot In [19]: #x axis- categories tty axis- Numerical #Bivariate analysis # Use case- Aggregate analysis of groups # Numerical vs Categorical In [4]: # Simple bar chart children=[2,5,6,9,10 color=["red”,"blue”, "green", "white", "yellow"] plt.bar(color, children) out[4]: » locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 20131 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [5]: # Color children=[2,5,6,9,10] color=["red","blue”, "green", "white", "yellow"] plt.bar(color, children, color="Yellow") out[5]: » In (6): # Horizontal bar chart (Barh) children=[2,5,6,9,10] color=["red","blue”, "green", "white", "yellow"] plt.barh(color, children) out[s]: yellow white geen locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb Fy 21131 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [7]: # Colour df= pd.read_csv("batsman_season_record.csv") df out [7]: batsman 2015 2016 2017 0 ABde Villiers 513 687 216 1 DAWamer 562 848 641 2 MSDhoni 372 284 290 3 RGShama 482 489 333 4 VKohli 505 973 308 In [9]: plt.bar(df["batsman" ],df["2015"]) out [9]: 8 8 8 8 8 ‘AB de Villiers OA Warner MS Dhoni RG-Sharma — V Kohl, locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 773, 14:27 PM Matploil-Jupyter Notebook In (11): #PLot multiple graph plt.bar(df["batsman"],d¢["2015"], width=.1) out (11): 500 200 100 ° AB de Villers DAWamner — MSDhoni RGSharma WV Kohli In [24]: plt.bar(np.arange(df.shape[0])-0.2,df["2015"], width=0.2,color="Red") plt.bar(np-arange(df.shape[0]),df["2016"], [email protected],color="Vellow") plt.bar(np.arange(df.shape[9])+0.2,df["2e17"], width=2.2,color="Blue") plt.xticks(np.arange(df.shape[@]), df["batsman"], rotation=60) plt.show() 1000 0 ao 0 m0 ol é ¢ $$ § #? ef ¢ bi & localhost 8888 /notebooks/3rd Semester/My Practce/MatpotibyMatpotibipyno 23931 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [25]: # Stacked bar chart df out [25]: batsman 2015 2016 2017 © ABde Villiers 513 687 216 1 DAWamer 562 848 641 2 MSDhoni 972 284 290 3° RGSharma 482 489 333 4 VKohli 505 973 308 In [29]: plt.bar(df["batsman"],df["2015"]) plt.bar(df["batsman"],df["2016"], bottom=df["2015"]) plt.bar(df["batsman"],df["2017"], bottom=df["2016"]+ df["2015"]) out[29]: ‘AB de Villiers DA Warner MS Dhoni RG Sharma V Kohli, locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 24031 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [30]: plt.bar(df["batsman"] ,df["2015"], label="2015") plt.bar(df["batsman"],df["2016"], bottom=df["2015"],label="2016") plt.bar(df["batsman"],d#["2017"], bottom=df["2016"]+ df["2015"], label="2017") plt.legend() plt.show out[3@]: ) 200 5 150 13s 100 07s 050 025 0.00 10 % 0 0 50 © In [22]: #Using Bins data=[32,45, 56, 10,15,27,61] plt.hist(data,bins=[10,25,40,55,70]) # Bin size is Large out [22]: (array([2., 2.) Les 2.1) array([1®, 25, 42, 55, 70]), ) 200 17s 150 125 100 075 050 025 0.00 locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 26131 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [23]: df= pd.read_csv("vk.csv") aft out (23): match_id batsman_runs ° 12 62 1 7 28 2 20 64 3 a ° 4 30 10 136 624 75 137 626 13 138 632 4 139 633 ° 140 636 84 141 rows * 2 columns In [25]: plt.hist(d#1["batsman_runs"], bins=[@,10, 20, 30,40,50, 60,70, 80,90,100,110,120]) plt.show() Bom Bm 8 In [26]: # Handling Bins Arr= np.load("big-array.npy") ar out[26]: array([33, 39, 37, ..., 33, 38, 39], dtype locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 27131 187128, 11:27 PM Maiplotib-Jupyter Notebook In [27]: Arr.shape out 27]: (11949, ) In [29]: plt-hist(Arr) plt.show() 000 $88 0 2» 2” 40 0 © 7 In [30]: # Some bins contains so many data that some bins are formed properly Pie chart In [32]: # Univariate/Bi-variate #Categorical Vs Numerical #Use case- To find the contribution on a standard scale locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 28131 187128, 11:27 PM Matploil-Jupyter Notebook In [33]: #Simple data df2= [23,45,100,20,49] plt.pie(df2) plt.show() In [36]: #Labels df2= [23,45,100,20,49] Subjects= ["Eng", "Hindi", "Maths", "Science", "History"] plt.pie(df2, labels-Subjects) plt.show() History locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 29131 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [37]: #ataset d#3= pd.read_csv("gayle-175.csv") #3 out[37]: batsman batsman_runs © AB4de Villiers 3 1 CHGayie 175 2 RRampaul 0 3 SS Tiwary 2 4 TMDilshan 33 5 V Koh 1" In [40]: plt.pie(df3["batsman_cuns"], labels=df3["batsman"]) plt.show() AB de Villers cH Gayle In [42]: # Showing Percentage plt.pie(df3["batsman_runs"], labels=df3["batsman"], autopct="%0.1f%%") pit. show() AB de Villers CH Gayle V koh ‘Tw Dilshan SRAmpay locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 30031 ‘HR, 11:27 PM Maiplotity - Jupyter Notebook In [44]: plt.pie(df3["batsman_cuns"], labels=dF3["batsman"], autopct="%0.1f%%", colors=| plt.show() “blue”, "gl AB de Villers cH Gayle In [47]: #ExpLoding plt.pie(df3["batsman_cuns"], labels=df3["batsman"], autopct="%0.1*%%" ,explode=[0,0,0.3,0 plt.show() AB de Villers cH Gayle ‘Tw Dilshan SS Twary RRampaul In[ ]: locahost 8888/notebooksiard Semester?My Practce/MatplotiiyMatpotibipynb 31131

You might also like