From 6128ecd80890bdd65006eb9bba12049fd009149b Mon Sep 17 00:00:00 2001 From: sunilhariharan Date: Tue, 9 Oct 2018 10:39:48 +0000 Subject: [PATCH 1/4] Done --- __pycache__/__init__.cpython-36.pyc | Bin 168 -> 161 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 193 -> 186 bytes .../__pycache__/build.cpython-36.pyc | Bin 630 -> 563 bytes q01_calculate_statistics/build.py | 11 ++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 199 -> 192 bytes .../__pycache__/test_q01_plot.cpython-36.pyc | Bin 2949 -> 2942 bytes 6 files changed, 10 insertions(+), 1 deletion(-) diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index cd8686b0f9f17c173480b2b430af88fa1427ca13..39e245becf97d3cdb55f7f2073c4da7cad02e2c1 100644 GIT binary patch delta 56 zcmZ3%xR8;G~P@xvBcarFoe-8Hq)iK%AJTAD&;7U0jfuoT{Ik KpOQK;D;xkSA{2oD delta 63 zcmdnRc#x69n3tDp*}dkdi5%wIdHNaoxvBbzNg0{?F8Rr&xv6<2#ro+*sg;Q(`MLUu SIXMaiMfq8&$tA@TlfwbEMi%z~ diff --git a/q01_calculate_statistics/__pycache__/build.cpython-36.pyc b/q01_calculate_statistics/__pycache__/build.cpython-36.pyc index 58a2a31fb42e0e24a3953e95448b0ffc0fa71daf..dcde0988b0078a72abddc3680f285d9398024178 100644 GIT binary patch delta 295 zcmYjMy-LL}6wY5uTD=ZVZh~8@QX@IGw9yO!d|uFHe)vIu@R7u=aTcRHL83=HihK3%2%c> zb2sR!SqWPKgw6|NuU#i(nM>$>e#OPZX3!Ew5KjNhhFq5TNDpmyX9+~hxD#3l=SioQ u+?GO}OLya$620)WG17+L=E3>?KiYtT=Z7F}Xv(7?+i@U{IZ5$0j(!0q97@&z delta 362 zcmY*Vy-LJD5Z>MF<&x+riiK9DO%=gT#73l}(ohxZ6` zQK>u>S>~6hQVwyYpKs{(YSamGj3bsuJ-W$o!^DBx4vIQ2=g3SJ*`+9?&}eswgCOK2 p*0YvNQHj>dRE*tkdSrjbKj)c7>zo>ibp~f0Tffbr4)f^l@DGsUW1#>5 diff --git a/q01_calculate_statistics/build.py b/q01_calculate_statistics/build.py index a556241..1e41766 100644 --- a/q01_calculate_statistics/build.py +++ b/q01_calculate_statistics/build.py @@ -1,11 +1,20 @@ +# %load q01_calculate_statistics/build.py # Default Imports import numpy as np import pandas as pd data = pd.read_csv('data/house_prices_multivariate.csv') -sale_price = data.loc[:, "SalePrice"] +sale_price = data.loc[:, 'SalePrice'] # Return mean,median & mode for the SalePrice Column # Write your code here +def calculate_statistics(): + mean=np.mean(sale_price) + median=np.median(sale_price) + counts=np.bincount(sale_price) + mode=np.argmax(counts) + return mean,median,mode + + diff --git a/q01_calculate_statistics/tests/__pycache__/__init__.cpython-36.pyc b/q01_calculate_statistics/tests/__pycache__/__init__.cpython-36.pyc index b1b01d55acae938b089c65022c1e5efe684e3182..fc496734bf17f488d7c2d922ec28f3c8992765a9 100644 GIT binary patch delta 56 zcmX@kcz}_^n3tF9e$$@li5%uCx%wITxvBcarFoe-8Hq)iK%AJTAD&;7U0jfuoT{Ik KpOQK;D;5ARO%$R4 delta 63 zcmX@Wc$|^Ln3tF9Mq+E!L=JQ968(()+*JLM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX?(%jU%l4AYzqSVU7lKfo# V#GD+3f};Ga)Z~)l%^w+iIROp-7>fV^ From 5260503881bcd4fc636ee93b91096786eb819fb1 Mon Sep 17 00:00:00 2001 From: sunilhariharan Date: Tue, 9 Oct 2018 10:46:56 +0000 Subject: [PATCH 2/4] Done --- q02_plot/__pycache__/__init__.cpython-36.pyc | Bin 177 -> 170 bytes q02_plot/__pycache__/build.cpython-36.pyc | Bin 775 -> 766 bytes q02_plot/build.py | 13 +++++++++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 183 -> 176 bytes .../__pycache__/test_q02_plot.cpython-36.pyc | Bin 969 -> 962 bytes 5 files changed, 13 insertions(+) diff --git a/q02_plot/__pycache__/__init__.cpython-36.pyc b/q02_plot/__pycache__/__init__.cpython-36.pyc index 215eac083bf88e6537e6d7d6a5471a2c374ca81c..ec1702a898f66da3f34006e2ad4cd4dfe80c23e3 100644 GIT binary patch delta 56 zcmdnUxQda(n3tF9TGO8Bi5%uC;rbc*xvBcarFoe-8Hq)iK%AJTAD&;7U0jfuoT{Ik KpOQK;%N+n9!W2OO delta 63 zcmZ3*xRH^=n3tDp*}dkdi5%wIarzngxvBbzNg0{?F8Rr&xv6<2#ro+*sg;Q(`MLUu SIXMaiMfq8&$tA@TlidNTmKL`F diff --git a/q02_plot/__pycache__/build.cpython-36.pyc b/q02_plot/__pycache__/build.cpython-36.pyc index bed076d1cc99b8e94b503c07bb460492f8d4c6bc..78a9ef0f55c520441a31ba97ffb447dbf3561d53 100644 GIT binary patch literal 766 zcmZuv%Wl*#6txpilF2-vRX1$e&1O;_%L*Z}uaJs_WP~D*?anxL9<`k*Wx-}Zd<*}; zmw3yHUtq;`I+PK@mXD9^>)dm$^K3TD=U>0Sdmkb610A#&_)8e}6M#ShYeexdM^#J- zut<;UgeDkCQl%o^VPLq*1leIamg6cHSl};_7+pq>5S@rbq@NL;Li9{dhGzGs4DQ;=Z*6WXt1#_&}w7r#OXB3yV ztb6U$mKg={OK!Jxe8IGQ9S(W;;-3cI(JL7CIeuyh3I#K%TLF7^)82eTW&)W9`1J-n)UvRB zqx1%}!(dJEwl!C_V_X&-t`$OBZd3>E4hsPZ+e&g*T%SHIJKefs)hjKQ-K{5KISU?h z0EF{>H(_saOp}f^f>|GRf*#e(g>bD_a5XSE9%d8%3VOCS@|L-_4gvovvCHezC*}X1 zX*q~7q1be8Ze+SYy{1WWTG6NC_Lk(VYT$JZn+sj_#o1dz>)xIfGj{T^S5?) gYzlimJA?A}TD}O1?Fm2zj;B%ZeN3`6$8+ev0U#I30ssI2 literal 775 zcmZuvO>fgM7`B}>O+!10i3{R_xaHD}ah(tnh~tFRo0$~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<$!Xb|#uv*@8#QmYeH_AYjmyvwI;BVS z7(aW2Q9k8KE7quhonXix*20H=qnEfhcvv4+I}Y`;zo0_HeJE~zb@IIY-_w{6Xa@Co yYC))ScnjgZTv|~>ADKql6mJ+%4XPZN85a8V3?=IfybS+f;F8jePFY5eN527_GSx8v diff --git a/q02_plot/build.py b/q02_plot/build.py index 70276d6..3fdb775 100644 --- a/q02_plot/build.py +++ b/q02_plot/build.py @@ -1,3 +1,4 @@ +# %load q02_plot/build.py # Default Imports import pandas as pd import matplotlib.pyplot as plt @@ -9,4 +10,16 @@ # Draw the plot for the mean, median and mode for the dataset +def plot(): + plt.hist(sale_price) + plt.axvline(mean) + plt.axvline(median) + plt.axvline(mode) + plt.show() + +plt.hist(sale_price) +plt.axvline(sale_price.mean()) +plt.axvline(sale_price.median()) +plt.show() + diff --git a/q02_plot/tests/__pycache__/__init__.cpython-36.pyc b/q02_plot/tests/__pycache__/__init__.cpython-36.pyc index 488a8902e9cb8aed0f38d008a72db519050c874f..ddca84f0f4bfcf22496ce976f9768d99def7b8f5 100644 GIT binary patch delta 56 zcmdnaxPg(wn3tF9TGO8Bi5%uCvHBVLxvBcarFoe-8Hq)iK%AJTAD&;7U0jfuoT{Ik KpOQK;%NGD7Mif~9 delta 63 zcmdnMxSf&1n3tF9Mq+E!L=JQ96#b0++*JLM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX Date: Tue, 9 Oct 2018 10:53:42 +0000 Subject: [PATCH 3/4] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 192 -> 185 bytes .../__pycache__/build.cpython-36.pyc | Bin 494 -> 558 bytes q03_pearson_correlation/build.py | 7 +++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 198 -> 191 bytes .../test_q03_correlation.cpython-36.pyc | Bin 1680 -> 1673 bytes 5 files changed, 7 insertions(+) diff --git a/q03_pearson_correlation/__pycache__/__init__.cpython-36.pyc b/q03_pearson_correlation/__pycache__/__init__.cpython-36.pyc index 543c178c4df3a2d7e5b64ffe37ce6264e5b948ea..28c9cd46aeeba777d2e6e38138155b4382a0ebc6 100644 GIT binary patch delta 56 zcmX@WxRa5?n3tF9TGO8Bi5%uCY5E!YxvBcarFoe-8Hq)iK%AJTAD&;7U0jfuoT{Ik KpOQK;D+~ZBj1+wU delta 63 zcmdnVcz}_^n3tDp*}dkdi5%wIx%wITxvBbzNg0{?F8Rr&xv6<2#ro+*sg;Q(`MLUu SIXMaiMfq8&$tA@TlfwYCn-=o` diff --git a/q03_pearson_correlation/__pycache__/build.cpython-36.pyc b/q03_pearson_correlation/__pycache__/build.cpython-36.pyc index ba8cf119e61bb596104a35e0bb902136188759a1..38997df0a533069bbfe48279206c1419374135a8 100644 GIT binary patch literal 558 zcmZWlu}&N@5FLAWkL3s-KuWrm5PLuyMUm3eq(Cyo%CUVqAG>Qa_97ihDiSHb64B%X z_>yg@?iXmtcnfqABh8!f^NjswE)EapkAI%7|1p4P*fCD|7xJ(m(4bihf=!W&%&>K? z`2!Qhlx397bgqkEAoeu-2Gwj!U2u7StYwt-$_>FZ9<4H=>4rAiJBe0CbE?AK{m1t; z%K1&YQ|Xmtqz(%5ujG@W2x}JkIwM8!o9k@Jk09o6=RBPsxGs+1C;Wh<=yIDL!35h^ zGR!Ee_(Wiuwkk&6dr>NfsGM1j2T9lxWoMc*k=xd(UFy7If-C$BxJS(|il*#L9fsbv zE1Hg6_Vty+o8YA~wQ}0j+60Bx)BL6hQAQi0Re?6+)<(tpc5%^oBQdzXNh(ZBC9bc( z54P2(els5Iupj8xkP`qqVYpARD#gspUdu3YuSL-ho!?+85hWU_8`>zQE#fReYMHd} ZKuO$Ke(IbaTJt$=C?u+6C7-i-@gHpUlU@J- 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..52bb381 100644 --- a/q03_pearson_correlation/build.py +++ b/q03_pearson_correlation/build.py @@ -1,5 +1,7 @@ +# %load q03_pearson_correlation/build.py # 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') @@ -7,3 +9,8 @@ # Return the correlation value between the SalePrice column for the two loaded datasets # Your code here +def correlation(): + cr=np.corrcoef(dataframe_1.iloc[:,-1],dataframe_2.iloc[:,-1])[0,1] + return cr + + diff --git a/q03_pearson_correlation/tests/__pycache__/__init__.cpython-36.pyc b/q03_pearson_correlation/tests/__pycache__/__init__.cpython-36.pyc index d7eca9980cd94014cb671238783d84df5e9fb7da..cf45f4eb4408c9fefa46fb9e947dd3f63dc6acee 100644 GIT binary patch delta 56 zcmX@cxSx^3n3tF9TGO8Bi5%uCIrM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX?(%jU%l4AYzqSVU7lKfo# W#GD+3f};Ga)Z~)l&BquIvj70*5f|?O From be1e97c4f6a7b8df00e27a81d3a33c1356a057b1 Mon Sep 17 00:00:00 2001 From: sunilhariharan Date: Tue, 9 Oct 2018 11:27:21 +0000 Subject: [PATCH 4/4] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 193 -> 186 bytes .../__pycache__/build.cpython-36.pyc | Bin 505 -> 746 bytes q04_spearman_correlation/build.py | 12 ++++++++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 199 -> 192 bytes ...st_q04_spearman_correlation.cpython-36.pyc | Bin 1717 -> 1710 bytes 5 files changed, 12 insertions(+) diff --git a/q04_spearman_correlation/__pycache__/__init__.cpython-36.pyc b/q04_spearman_correlation/__pycache__/__init__.cpython-36.pyc index 78682675323d8e4b951373280266bfae3fe10d8b..99479bf41dbeddc12c61e3f8bc666d2d5af6ba0f 100644 GIT binary patch delta 56 zcmX@exQmg)n3tF9TGO8Bi5%uC>G~P@xvBcarFoe-8Hq)iK%AJTAD&;7U0jfuoT{Ik KpOQK;D;xkSA{2oD delta 63 zcmdnRc#x69n3tDp*}dkdi5%wIdHNaoxvBbzNg0{?F8Rr&xv6<2#ro+*sg;Q(`MLUu SIXMaiMfq8&$tA@TlfwbEMi%z~ diff --git a/q04_spearman_correlation/__pycache__/build.cpython-36.pyc b/q04_spearman_correlation/__pycache__/build.cpython-36.pyc index 94f735a46faa9e694e8a6b3b49b480cf37144bf0..76926522e29eb250472675dc66381d3d1b15124c 100644 GIT binary patch literal 746 zcmZuv&2H2%5VoD4&8Dp=We;7rAr9=Np@riLA#tyeii8vnk@1+;+r$aBv!d1Rsaz{~ z2rj$>PvR@5eFaX8)5{`oG@s|^^Efl(=X-nk*Ka@HH;j;9WNV>KUZL2h2ta_=q@3*Kzc}!gZqlE$Ro_UW-EqW z*gY-BXS|kgLgjB~v>bCQqz0wW%fxVfd3?8>Y$%q5@tA*B)>GJou9pn#CJlki?}Q$G zG`x}3aT$lB+pZJOI`FAzwcyT2wr_m8t^3wDRt9x$Jkfvk=!4NLg>UHlPBq@4g6n3r zQ0LyP9riJ(Tfzs3-YMw1#X!DA6T{1axT;06GEQ5Gt3nq8^cKP>2CGX#u(b*Iluhx| dC!4juYrkEQgt0tv-mW`5o$|soDuv`S{{f%VN234$ diff --git a/q04_spearman_correlation/build.py b/q04_spearman_correlation/build.py index 557be32..4afbb55 100644 --- a/q04_spearman_correlation/build.py +++ b/q04_spearman_correlation/build.py @@ -1,3 +1,4 @@ +# %load q04_spearman_correlation/build.py # Default Import import pandas as pd @@ -5,4 +6,15 @@ dataframe_2 = pd.read_csv('data/house_prices_copy.csv') # Your code here +def spearman_correlation(): + dataframe_1['rank1']=dataframe_1['SalePrice'].rank(ascending=True) + dataframe_2['rank2']=dataframe_2['SalePrice'].rank(ascending=True) + d=pd.concat([dataframe_1, dataframe_2], axis=1) + d['d']=d['rank1']-d['rank2'] + d['ds']=d['d']**2 + n=6*sum(d['ds'].values) + d=len(d['d'].values)*(len(d['d'].values)**2-1) + spear_corr=1-(n/d) + return spear_corr + diff --git a/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc b/q04_spearman_correlation/tests/__pycache__/__init__.cpython-36.pyc index 495646a3bc5e900ad0593288f8e14eb5f8ed301b..2be4d8b719ab5b9fd3fbd4ddf63dd06ef7b82e22 100644 GIT binary patch delta 56 zcmX@kcz}_^n3tF9TGO8Bi5%uCx%wITxvBcarFoe-8Hq)iK%AJTAD&;7U0jfuoT{Ik KpOQK;D;5APrWBa~ delta 63 zcmX@Wc$|^Ln3tF9Mq+E!L=JQ968(()+*JLM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX