From 6d29f77b5df11b15f26a94ce0d5082f0efd66f63 Mon Sep 17 00:00:00 2001 From: vivekshingate Date: Sat, 10 Nov 2018 15:40:15 +0000 Subject: [PATCH 1/4] Done --- __pycache__/__init__.cpython-36.pyc | Bin 163 -> 155 bytes .../__pycache__/__init__.cpython-36.pyc | Bin 177 -> 169 bytes .../__pycache__/build.cpython-36.pyc | Bin 560 -> 612 bytes q01_cond_prob/build.py | 15 +++++++++++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 183 -> 175 bytes .../test_q01_cond_prob.cpython-36.pyc | Bin 1691 -> 1683 bytes 6 files changed, 15 insertions(+) diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index 2ba0c8128ed226d8795f0b8b0cc1481272d86b4c..23b89f16c5852328aab49c2232ad465e3c825049 100644 GIT binary patch delta 55 zcmZ3?IGd5fn3tE!_vf?di5%w29{L&ixvBbPnPsWj#Tl7->4_z&`r-LS*~JBk$*KCu K`6;Orvn&Azz!SXy delta 63 zcmbQuxR{Z{n3tF9(7ooUi5%wI0s0yFxvBbzNg0{?F8Rr&xv6<2#ro+*sg;Q(`MLUu SIXMaiMfq8&$tA@TlPm$I;})3! diff --git a/q01_cond_prob/__pycache__/__init__.cpython-36.pyc b/q01_cond_prob/__pycache__/__init__.cpython-36.pyc index a5c1ab27a925d7c6ab904d43c42e33fb15ea64d6..cee39dfd87cdbb6688365c48509964a5ba02941e 100644 GIT binary patch delta 55 zcmdnUxRQ~>n3tE!_vf?di5%w2Vfq>QxvBbPnPsWj#Tl7->4_z&`r-LS*~JBk$*KCu K`6;Orv)lm>$`kbf delta 63 zcmZ3ab diff --git a/q01_cond_prob/__pycache__/build.cpython-36.pyc b/q01_cond_prob/__pycache__/build.cpython-36.pyc index 4654504299c0bacbf40adc47f518204d14780447..6898a309d3c99022a324adbd978c2236b0f63888 100644 GIT binary patch delta 369 zcmYk2u};G<5QfiA(uR5 z_dwzSSV6o4uy9Ek>eK!Dzu)KK{GxuUt&U|GZ@*vHJ_Y!Ije`s)*janoa&%tf+JX>R zo*mEYm@3%a^7aNrVli?6jK&ld-5o5TAnUa9R1!%Kp-?1YN)se461eHe1^1K@n_(M;-0&+XvX6#jFRyv=kAqA<813; o6mT~XjIW-^>D~@b18owM>cl2CHRu2QWrs^jqWn}8R!%l`RwkC@ z=jsDZRRAi_N=*ieX6B`(76Iimfo2q!Bu?JNXvo6>G=zbXi&2bGgK_d-#xQ4_z&`r-LS*~JBk$*KCu K`6;OrvwQ&)#uN|$ delta 63 zcmZ3_xSf&1n3tF9Mq+E!L=JQ96#b0++*JLM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAXn>g Date: Sun, 11 Nov 2018 10:08:27 +0000 Subject: [PATCH 2/4] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 187 -> 179 bytes .../__pycache__/build.cpython-36.pyc | Bin 718 -> 911 bytes q02_confidence_interval/build.py | 28 +++++++++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 193 -> 185 bytes ...est_q02_confidence_interval.cpython-36.pyc | Bin 2316 -> 2308 bytes 5 files changed, 27 insertions(+), 1 deletion(-) diff --git a/q02_confidence_interval/__pycache__/__init__.cpython-36.pyc b/q02_confidence_interval/__pycache__/__init__.cpython-36.pyc index 741ad2df56ebd795144517f30579112c8725c917..670cbf189a68c98b1b0592de73a1fe294b1c84f8 100644 GIT binary patch delta 55 zcmdnZxS5f|n3tE!_vf?di5%w23HllNxvBbPnPsWj#Tl7->4_z&`r-LS*~JBk$*KCu K`6;OrvjPDXh!hlXO{ diff --git a/q02_confidence_interval/__pycache__/build.cpython-36.pyc b/q02_confidence_interval/__pycache__/build.cpython-36.pyc index b478df2185179a11ca8a5a753fb3aedba6bb2ba4..1910cffc91c3b06cede5cd6c8c4bb7791d72df74 100644 GIT binary patch literal 911 zcmZuvOK%e~5VpOKY!bCa1r;hJlxr?sL~jW35JGS$;ZPwYBeZhY-e$M^aBU~hYI6$L z9+CJ9{3TyGATIm>E->EY5Kw33nQuOi$KTpM+}avk{rU0!i;vKEv|$ABQyBUcIF2|j z5nV-G5K216qkb0y8VbMYak9iT5)t?I5$$uI2cHogh=J%YF@_GuXdM28ZfJ73$C+XA zw3%s*|_A&xLH=HOZ`ZVk8*OM`}`22ErGWypZjxKjUB_~X6(2k=Uxr2^7 zzJ`0v)M;LinrtMLYE)Nu)O-|bbd*=Q=~lS4Z>9W?8~1IXr%Vd!SAx}$7-qEf>qb@7 zlQN^8Hr)CZGgIs9b7gD*w^N&OWJAp=Sqh6MH0ab@Of5d9J1aTKn=EDyLd{tjpUm=-AIJ-P^P1T$_jc}qLu7y>ybWWQL^y(M<0I+@ zRE&qJ2Z0WCn#+rWZg&*`V?)Vm&a@?x)1aPJuon zZAIiDU4DT7MFiVz(_2Z3RKDFbKKQ;{L@r(Wy-nk;k5~ zQk}&^W5rAgEyqghQZF9a>gW!1KrjAN(X=d7B)(76=%7qa3pKMQI??J}*s_R3p1-Sf znW@B@#V_{dvtFjD7N#XYABTiBe1qLd7-*klij<_)`6n{AM)So7Cp;XG-f&Gx%A(=P jv`iD#&2&Lt(XhSf?-Zpx&DAb_BbZk5u}@ANyDRttekpUU diff --git a/q02_confidence_interval/build.py b/q02_confidence_interval/build.py index 023b81e..d7f529e 100644 --- a/q02_confidence_interval/build.py +++ b/q02_confidence_interval/build.py @@ -1,13 +1,39 @@ +# %load q02_confidence_interval/build.py # Default imports import math import scipy.stats as stats import pandas as pd import numpy as np df = pd.read_csv('data/house_pricing.csv') -sample = df['GrLivArea'] +sample = df['GrLivArea'] #Sampling Analysis on GrLivArea + # Write your solution here : +def confidence_interval(sample): + + N = sample.shape[0] #Length of sample + x_bar = sample.mean() #Sample mean + Z = stats.norm.ppf(q = 0.95) #Z-critical + S = sample.std() #S - Sample standard deviation + Margin_Of_Error = Z*(S/math.sqrt(N)) #estimate to be subtracted/added from mean + + Lower_limit = x_bar - Margin_Of_Error #Lower limit of confidence interval + Upper_limit = x_bar + Margin_Of_Error #Upper limit of confidence interval + + print('N : ',N) + print('x_bar : ',x_bar) + print('Z : ',Z) + print('S : ',S) + print('Margin of error : ',Margin_Of_Error) + print('Lower Limit : ',Lower_limit) + print('Upper Limit : ',Upper_limit) + + return Lower_limit,Upper_limit + +#Call to the function +confidence_interval(sample) + diff --git a/q02_confidence_interval/tests/__pycache__/__init__.cpython-36.pyc b/q02_confidence_interval/tests/__pycache__/__init__.cpython-36.pyc index 2eb0cc486e78e2a412ba8dab98d1f27df5f7cde5..7da332e31d6dff048a11966c4ec46df436381957 100644 GIT binary patch delta 55 zcmX@exRa5?n3tE!_vf?di5%w2Y5E!YxvBbPnPsWj#Tl7->4_z&`r-LS*~JBk$*KCu K`6;Orv%&!w`V=() delta 63 zcmdnVc#x69n3tF9Mq+E!L=JQ9JpGLP+*JLM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAXS$qU_>=#N<@{ N&GJld*#KT06-)pC delta 66 zcmZn>>Jj2F=H=zOk=Powk>d@cc9VWaer~FMVp2w?zDs^`X>Mv>NwI! Date: Tue, 13 Nov 2018 17:12:05 +0000 Subject: [PATCH 3/4] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 174 -> 166 bytes q03_t_test/__pycache__/build.cpython-36.pyc | Bin 523 -> 609 bytes q03_t_test/build.py | 11 ++++++++++- .../tests/__pycache__/__init__.cpython-36.pyc | Bin 180 -> 172 bytes .../test_q03_t_test.cpython-36.pyc | Bin 2307 -> 2299 bytes 5 files changed, 10 insertions(+), 1 deletion(-) diff --git a/q03_t_test/__pycache__/__init__.cpython-36.pyc b/q03_t_test/__pycache__/__init__.cpython-36.pyc index cac7d291ce27aa37820fd1dcd256be95534d4e6d..9648422a8f51db7560a8add75e7b0d1c1c5a3ddb 100644 GIT binary patch delta 55 zcmZ3-xQvm*n3tE!_vf?di5%w2!TK5bxvBbPnPsWj#Tl7->4_z&`r-LS*~JBk$*KCu K`6;Orvs?fU5fkYE delta 63 zcmZ3+xQ>y-n3tF9(7ooUi5%wI(fS$rxvBbzNg0{?F8Rr&xv6<2#ro+*sg;Q(`MLUu SIXMaiMfq8&$tA@TlUx9d8~c zNuR+N@aA*GlXwze!GoKe9GIDJVE$odp2#P;KWev~E&6lQ!U%n#e`acQW?Y?{AdrAD z8Ulx!Ft_SVI58QIX<~C5khF$t!dd}mf(ZJ6ctbWMTLBpL74qzFGYMUIP|}5#N-s7= zkn=-0$sgUl6~4twSYmBuP$@E;VL?WykByS%?{0JO@?6>5sYmkP?e&t*(s-ghtHh$u zn~S0YJMN_)O%v(Qdne;Tq-##APn9f{f#`*5o>Eh$toVTa4a=Zv Onc$eY3|iR1%>DzO1zqC+ delta 356 zcmYjNu}T9$5Z&3^yM!FU)=njjr;tMg3mYvgtZW34ML5>mO>*%rx9n~LqCrGEu?VRY z{DAmL*NK(n53HO^AsQ>;}+u|tlD&IQcEDxPi)+KvZ6q>Udgfl98Rp^o$ky)3exFDH`e5@A4 z1bF-RG9HwLipBLHi%-gQT&R(=ao?z0;mRTwdA_MlIaFTi?EDeBr^ZKGh+!Ef0z0tk yL=7I=G}E`;l^WyWtO~RkNntChWz{rF$RxEBQ}c{J-=$k?_1kQ%qXkXc3jP4^iC*gf diff --git a/q03_t_test/build.py b/q03_t_test/build.py index f966b62..971b691 100644 --- a/q03_t_test/build.py +++ b/q03_t_test/build.py @@ -1,9 +1,18 @@ +# %load q03_t_test/build.py # Default imports import scipy.stats as stats import pandas as pd +import math +from statsmodels.stats.weightstats import ztest df = pd.read_csv('data/house_pricing.csv') +def t_statistic(df): + #z_statistic, p_value = ztest(x1=df[df['Neighborhood']=='OldTown']['GrLivArea'], value=df['GrLivArea'].mean()) + z_statistic, p_value = stats.ttest_1samp(df[df['Neighborhood']=='OldTown']['GrLivArea'],df['GrLivArea'].mean()) + print(z_statistic) + return p_value,p_value<0.1 #As significance level is 90% hence 0.1 + +t_statistic(df) -# Enter Code Here diff --git a/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc b/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc index c48929092cfb36da263304e1c41ce26f2e59ebaa..0ec7db86729325eeff521d51a0a765f421dc2580 100644 GIT binary patch delta 55 zcmdnOxQ3C#n3tE!_vf?di5%w2k@^|=xvBbPnPsWj#Tl7->4_z&`r-LS*~JBk$*KCu K`6;Orv%CNigA@S( delta 63 zcmZ3(xP_6!n3tF9Mq+E!L=JQ9ME#8X+*JLM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX?(%jU%l4AYzqSVU7lKfo# W#GD+3f};Ga)Z~)l&HotxvH<`J Date: Wed, 14 Nov 2018 18:27:49 +0000 Subject: [PATCH 4/4] Done --- .../__pycache__/__init__.cpython-36.pyc | Bin 177 -> 169 bytes .../__pycache__/build.cpython-36.pyc | Bin 604 -> 660 bytes q04_chi2_test/build.py | 27 ++++++++++++++++++ .../tests/__pycache__/__init__.cpython-36.pyc | Bin 183 -> 175 bytes .../test_q04_chi2_test.cpython-36.pyc | Bin 1938 -> 1930 bytes 5 files changed, 27 insertions(+) diff --git a/q04_chi2_test/__pycache__/__init__.cpython-36.pyc b/q04_chi2_test/__pycache__/__init__.cpython-36.pyc index 07afcf050f12f3301d4c6770275250f5d539aa29..8ff21eccdc542105e650dc39e4c233c7554fc731 100644 GIT binary patch delta 55 zcmdnUxRQ~>n3tE!_vf?di5%w2Vfq>QxvBbPnPsWj#Tl7->4_z&`r-LS*~JBk$*KCu K`6;Orv)lm>$`kbf delta 63 zcmZ3ab diff --git a/q04_chi2_test/__pycache__/build.cpython-36.pyc b/q04_chi2_test/__pycache__/build.cpython-36.pyc index 699bd6ac19c2845f16b2ff9f235a37aaeb9035d3..748490c4723b0d6038ba0fd9ed84d07e5f2c916b 100644 GIT binary patch delta 501 zcmYjNO>fjN5cO9aC)CZjQy z@da+NXMzSbc!gTxr)fi0@QAcQOWUwz4Q+x3PDzGFAQ^leXT9Bgxau?|IdX9Bkj!}W zB|Vj+qO25;MrolAjTY+49|Ab}q{lg@GbQz6=5SH|NT8!ddZG%Ogf6gkT3bg%u3vLp zRhdJTM4E$7!vG-%2yJRVvg_lv1t#!gs$0zS(a00LT_*a2IXBN7Ov@c@px06}mcm z*~>G`*Bq_q6f+Y>{EV#2oX0IQLF AO8@`> delta 458 zcmYjOyH3L}6tx}a(E?Io0wyE|$N-UGJNAFuv5UfrIXYj;*Yh=Kt8fPaQueBj)yKd-JmpKn}+E(x3; zHpOEH77SqtI9vi8agSr}_dOmwc@=aW+EG7E;D%RYbxSkiaoO9gBXO?; zvx0vD-Es^5UM2&Xi-dLuX>uglI2VOANneWzwK7j=maQl)hfZT&zToctY;&5(0f5V} z0~es4ad8}y8N*UF*_;ljeOIdk<<_D`<0gr;p!}MdTiqOZDw+=P586}SPA>U46MM~b LOv7!%2(`mMTuyj@ diff --git a/q04_chi2_test/build.py b/q04_chi2_test/build.py index 4f20455..60a2a80 100644 --- a/q04_chi2_test/build.py +++ b/q04_chi2_test/build.py @@ -1,3 +1,5 @@ +# Need to check this. This is wrong I guess. +# %load q04_chi2_test/build.py # Default imports import scipy.stats as stats import pandas as pd @@ -6,5 +8,30 @@ # Enter Code Here +def chi_square(df): + + # Find the critical value for 95% confidence* + # Df = number of variable categories - 1 + crit = stats.chi2.ppf(q = 0.95,df = 2) + #print('Critical value : ',crit) + + x = df['LandSlope'] + y = pd.qcut(df['SalePrice'],3,labels=['High', 'medium', 'low']) + + freqtab = pd.crosstab(x,y) + chi2,pval,dof,expected = stats.chi2_contingency(freqtab) + + #print('Chi-square test statistic : ',chi2) + #print('P-Value : ',pval) + + # If chi-square value exceeds critical value, reject the Null hypothesis viz. return False + return pval,(chi2>crit) + + + + +#Call to the function - +chi_square(df) + diff --git a/q04_chi2_test/tests/__pycache__/__init__.cpython-36.pyc b/q04_chi2_test/tests/__pycache__/__init__.cpython-36.pyc index 45a1b92bf8f907964bb7391c2292492de4735b27..182e6b15393d677fb1008eda4b1c2627b79f22ad 100644 GIT binary patch delta 55 zcmdnaxSo;2n3tE!_vf?di5%w2G5Q(#xvBbPnPsWj#Tl7->4_z&`r-LS*~JBk$*KCu K`6;OrvwQ&)JQNK8 delta 63 zcmZ3_xSf&1n3tF9Mq+E!L=JQ96#b0++*JLM~`m;B_?+|<01V*T`@)XKz?{9OIS SoE(LMqWrAX?(%jU%l4AYzqSVU7lKfo# W#GD+3f};Ga)Z~)l%^w+OvH}3@z!(z%