From 84dfbcbbe44c94ed2820162d27df91319b3240e3 Mon Sep 17 00:00:00 2001 From: Abhimanyu22 Date: Sat, 13 Oct 2018 05:35:42 +0000 Subject: [PATCH 1/4] Done --- __pycache__/__init__.cpython-36.pyc | Bin 168 -> 158 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 193 -> 183 bytes .../__pycache__/build.cpython-36.pyc | Bin 630 -> 539 bytes q01_calculate_statistics/build.py | 13 ++++++++++--- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 199 -> 189 bytes .../__pycache__/test_q01_plot.cpython-36.pyc | Bin 2949 -> 2939 bytes 6 files changed, 10 insertions(+), 3 deletions(-) diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index cd8686b0f9f17c173480b2b430af88fa1427ca13..c994ae5954ac0f5e57b3309f6b49bb4b1d8fe589 100644 GIT binary patch delta 53 zcmZ3%IFFITn3tDJr1oI+L=JOBZ~ct?+*EzXq>Rkm#JtKRkm#JtKw zH4^enSuD*ADU6Z~wM;b(HHl@pY)#Hvta+um1(iiiKwcDEL1JD?V(~4ef|SV`Ot!)x`-{1N1P3Dr L6BnZp69)$X9al53 delta 329 zcmbQu@{L8=n3tE!|HYiB?~Du#j~S2vGmz~7#Kjg9mCYw6c*L*(InE#f10Yetki}TS z)XZ25VljhRj3q2ttXXVeHd75l4Py;c7JCY#Btsf=FoPyjm56IzNotWoWqxUqLUMje zszOF;QECy;S_Vyyi7(~rnF>;(*n(4wGE<9hvE%|3++r(B%qdMR)?|+2FHX!!jV~z5 zOiqo@O-;;;5=0S5$pi|ar~ztU$xy@zH2hb#enx(7s(xZpMy9??esXDUYFRkm#JtKM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX?(%jU%l4AYzqSVU7lKfo# V#GD+3f};Ga)Z~)l&F>g{IROnV7=-`; From b77c3a7ef1e2842f26d3bc363f10aac9a8e2c44c Mon Sep 17 00:00:00 2001 From: Abhimanyu22 Date: Sat, 13 Oct 2018 05:53:25 +0000 Subject: [PATCH 2/4] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 192 -> 182 bytes .../__pycache__/build.cpython-36.pyc | Bin 494 -> 600 bytes q03_pearson_correlation/build.py | 15 ++++++++++++--- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 198 -> 188 bytes .../test_q03_correlation.cpython-36.pyc | Bin 1680 -> 1670 bytes 5 files changed, 12 insertions(+), 3 deletions(-) diff --git a/q03_pearson_correlation/__pycache__/__init__.cpython-36.pyc b/q03_pearson_correlation/__pycache__/__init__.cpython-36.pyc index 543c178c4df3a2d7e5b64ffe37ce6264e5b948ea..1d14a09461c167c705f5903bcdd0c437c420732f 100644 GIT binary patch delta 53 zcmX@WxQ&s+n3tDJr1oI+L=JPsWc`f%+*EzXq>Rkm#JtKweEdv*+4cIZQ9%`Vw)0RrtTgzt>FQA3E38z2 zW9{$PZ~o_K>sIki$0~6pfA=Mw{+uANWz@u;gy9Qu#2#1>|73VbmZJ^Z@U1W-Vu+0( zW$CrtyHPcKifWK%XU`FGv5PSdpQrsSYFeObpgif5+Uj9u-iy}BOj|^4VUZ_t=BeVJ z0Z)dPdC&1D!;Ff)d?gziC_diaRgG#_-F#krw)o9ErJ>N)Kw-dZtQ@%mr4K4pK2+LM zS-S)sitq1EO9u+QZOhmjYNFV-xb3Ri9J^IN8)PTc(#O6`9P&ecz;Q}(p2@LOtx>)g z&d9Xw8n?nRy~qqfnUXxm=ryJh;+LKH0qjw(&)zrIbTwQ=>wKhTJQGts71`t!l?0py literal 494 zcmZWlu};G<5Veyu4XwH`A_l}nmImmG5E9H4QnxITYacX`9UI%JR90B|1U`UY%F4tq zFmWy*Dsj?1J>8w&y}Q|DGBSs+rJ{tqlbwi=Utziv1VIFqq@+NbNJLMxjJGUCmWV_Q zo=G_nbV2g;1Eov1A^DyOZ{dn+yhHJA4JswnkBSCVF z>GlykY0!g@8!D)XULxEX&�!W}R+x+NTQqN{c+{$3g$jG6mIHxwl{vZiACP;o92W z?)e+BDQa)wvq9Sm3btI;#f|2jg4Vm@-ol1?tqLaPk+He~j#UAU+uGn=P&vt<8 diff --git a/q03_pearson_correlation/build.py b/q03_pearson_correlation/build.py index 33a762b..a2d425c 100644 --- a/q03_pearson_correlation/build.py +++ b/q03_pearson_correlation/build.py @@ -1,9 +1,18 @@ -# Default Imports import pandas as pd +import numpy as np dataframe_1 = pd.read_csv('data/house_prices_multivariate.csv') dataframe_2 = pd.read_csv('data/house_prices_copy.csv') +def correlation(): + + sale_price1 = dataframe_1.loc[:, 'SalePrice'] + sale_price2 = dataframe_2.loc[:, 'SalePrice'] + r = np.corrcoef(sale_price1, sale_price2)[0,1] + return r + +correlation() + + + -# Return the correlation value between the SalePrice column for the two loaded datasets -# Your code here diff --git a/q03_pearson_correlation/tests/__pycache__/__init__.cpython-36.pyc b/q03_pearson_correlation/tests/__pycache__/__init__.cpython-36.pyc index d7eca9980cd94014cb671238783d84df5e9fb7da..7d90f82c14befae31550a8049fb044779adc73ab 100644 GIT binary patch delta 53 zcmX@cxQCI$n3tDJr1oI+L=JPsO#O`f+*EzXq>Rkm#JtKM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX?(%jU%l4AYzqSVU7lKfo# W#GD+3f};Ga)Z~)l&4(Eevj70)KNsl$ From 14717b18d0e7c8833a3426e77250c43f154df0fd Mon Sep 17 00:00:00 2001 From: Abhimanyu22 Date: Sat, 13 Oct 2018 07:17:11 +0000 Subject: [PATCH 3/4] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 193 -> 183 bytes .../__pycache__/build.cpython-36.pyc | Bin 505 -> 687 bytes q04_spearman_correlation/build.py | 19 ++++++++++++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 199 -> 189 bytes ...st_q04_spearman_correlation.cpython-36.pyc | Bin 1717 -> 1707 bytes 5 files changed, 17 insertions(+), 2 deletions(-) diff --git a/q04_spearman_correlation/__pycache__/__init__.cpython-36.pyc b/q04_spearman_correlation/__pycache__/__init__.cpython-36.pyc index 78682675323d8e4b951373280266bfae3fe10d8b..da569297c716542e5567266f9449398150fc3edb 100644 GIT binary patch delta 53 zcmX@exSf&1n3tDJr1oI+L=JPs6#b0++*EzXq>Rkm#JtK=xF@=+mBDb7{E_BIGpfX68nmj0>w(m*l_bK zK(-1M-?1zjP(UbFp^CmhHp0;k7{y<}Jl<0-oNt~f(Ten{=`7~j6cTM-b!A)J2vdj_ zPo=%tJpMmMHhS%S(pT{(CW%Pilh~3}3oAbpeC3KQ`6F2I9c-ZuZn3f+dNu>ak73K( za2545|27~L4=7ZD3j1IRec01($Do24OyLR4U>o%jZ4;emcP>PUAN&S;&(EGngT0?> zK5`Skz|x2c^D`Hejm$zL>gz-M!tq+Wz;=}jZLz_5oJ}lM{71^!;m^X2Rk2*6!CIo@ z);d-@X1;^DPwoDAHY-fuU0xNHsMp)>22;2HMjRj0Y70U>@FMA_mr83WSJ*f ztVOMabzG|~s=G?BO+ub5F(_0{Pig$~8DC{c8J0Ov56Iz?*Hxps65n`s?U+=;5>AbH GGWiQmGq&&m delta 348 zcmYjMyGq1B6rERMHnNSi!j`5AYAYgWWg)^M$~4QEJDQD|OqiJ!tSq#(kOezGz{=l| zw0?zF-o(Paa1Mui?(-x1<|ljOar(OXCbuXdUt}d1>O+LzMgjt~CX#AeF<_5W@uKpr6~kv_|LZs+>>qV_PhYZi3HmoW57Vnq1ZO zq;f*-N7ME13}yc-|5S`dm+Tu0 Qi&`J_^L(F5SV~jz3*HV=BLDyZ diff --git a/q04_spearman_correlation/build.py b/q04_spearman_correlation/build.py index 557be32..ae77d96 100644 --- a/q04_spearman_correlation/build.py +++ b/q04_spearman_correlation/build.py @@ -1,8 +1,23 @@ -# Default Import import pandas as pd +import numpy as np dataframe_1 = pd.read_csv('data/house_prices_multivariate.csv') dataframe_2 = pd.read_csv('data/house_prices_copy.csv') -# Your code here +def spearman_correlation(): + + sale_price1 = dataframe_1.loc[:, 'SalePrice'].rank() + sale_price2 = dataframe_2.loc[:, 'SalePrice'].rank() + difference = (sale_price1 - sale_price2)**2 + ss = np.sum(difference) + n = np.size(difference) + r = 1-((6*ss)/(n*(n**2-1))) + return r + + +spearman_correlation() + + + + diff --git a/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc b/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc index 495646a3bc5e900ad0593288f8e14eb5f8ed301b..88c87f54a59698f8b763830e80ffdae4abcdbd30 100644 GIT binary patch delta 53 zcmX@kxR;T`n3tDJr1oI+L=JPsEd7l9+*EzXq>Rkm#JtKM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX Date: Sat, 13 Oct 2018 18:33:19 +0000 Subject: [PATCH 4/4] Done --- q02_plot/__pycache__/__init__.cpython-36.pyc | Bin 177 -> 167 bytes q02_plot/__pycache__/build.cpython-36.pyc | Bin 775 -> 844 bytes q02_plot/build.py | 19 ++++++++++++++++-- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 183 -> 173 bytes .../__pycache__/test_q02_plot.cpython-36.pyc | Bin 969 -> 959 bytes 5 files changed, 17 insertions(+), 2 deletions(-) diff --git a/q02_plot/__pycache__/__init__.cpython-36.pyc b/q02_plot/__pycache__/__init__.cpython-36.pyc index 215eac083bf88e6537e6d7d6a5471a2c374ca81c..724baf026f46973f5ca022c23661e36e46b5793f 100644 GIT binary patch delta 53 zcmdnUxSWy0n3tDJr1oI+L=JPs5dDn&+*EzXq>Rkm#JtKJf!AQo%SOgsggo{*!9i|gGDW(Do{Edj{j2t4mCt@-Bis($vI)owa zDVis@kOQ5}asPxf&0Ec!%&lWiS*N(A0o!c8JQK{ZY+JWh=8aKY+PrMFQs7-GXqaz&^7hMF5qN8>km_A>5-5i9m!m{APb?R3+fgM7`B}>O+!10i3{R_xaHD}ah(tnh~tFRo0$~3_B-mxX)@a>6s@Pifx~_R zKY+iKE2sShPQ1=QR1=Q;`u(!~JWu>$Hp@<*eCOX7AwS8%h|qt9)4fHbh@ysYI;^aU zc#Ix1qdMUUB|xjOiuRPJkX92#75&Ooe90aYo~e;az7YOE(FMuJw|Evg&uRZi3L`rs zJe1B0ubtP@eSW5d7saaS9F(oq5?on##_Nr+8e8YmZTMs%47>|P84e30KuvJI#_2B5 zc(NxK(T?osj(J)!A0a4q!zjThz9uSCaR7D`|H;t%89%C$YqlSV{p(dEkT~zDL<%F> zn8x;W$rB~q3e+u1Nb<aDB27rURFw<~4{lPijzFtoyib6#O7|iU$)&keF5Aq}45|dZ;}@80y8<$!Xb|#uv*@8#QmYeH_AYjmyvwI;BVS z7(aW2Q9k8KE7quhonXix*20H=qnEfhcvv4+I}Y`;zo0_HeJE~zb@IIY-_w{6Xa@Co yYC))ScnjgZTv|~>ADKql6mJ+%4XPZN85a8V3?=IfybS+f;F8jePFY5eN527_GSx8v diff --git a/q02_plot/build.py b/q02_plot/build.py index 70276d6..5641973 100644 --- a/q02_plot/build.py +++ b/q02_plot/build.py @@ -1,5 +1,5 @@ -# Default Imports import pandas as pd +import numpy as np import matplotlib.pyplot as plt from greyatomlib.descriptive_stats.q01_calculate_statistics.build import calculate_statistics @@ -7,6 +7,21 @@ dataframe = pd.read_csv('data/house_prices_multivariate.csv') sale_price = dataframe.loc[:, 'SalePrice'] +def plot(): + plt.figure() + sale_price.hist(bins=60) + plt.axvline(x=sale_price.mean(),label='mean') + plt.axvline(x=sale_price.median(),label='median') + plt.axvline(x=np.array(sale_price.mode())[0],label='mode') + plt.legend() + plt.show(); + + return + + +plot() + + + -# Draw the plot for the mean, median and mode for the dataset diff --git a/q02_plot/tests/__pycache__/__init__.cpython-36.pyc b/q02_plot/tests/__pycache__/__init__.cpython-36.pyc index 488a8902e9cb8aed0f38d008a72db519050c874f..4eb8f149f48464ba996ce799b2a75d45c561914f 100644 GIT binary patch delta 53 zcmdnaxR#N_n3tDJr1oI+L=JPsDE*B5+*EzXq>Rkm#JtKxSf&1n3tF9Mq+E!L=JQ96#b0++*JLM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX