commit-live-students · preetiail · Nov 7, 2018 · Nov 7, 2018 · Nov 7, 2018 · Nov 8, 2018
diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_cond_prob/__pycache__/__init__.cpython-36.pyc b/q01_cond_prob/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_cond_prob/__pycache__/build.cpython-36.pyc b/q01_cond_prob/__pycache__/build.cpython-36.pyc
diff --git a/q01_cond_prob/build.py b/q01_cond_prob/build.py
@@ -1,12 +1,21 @@
+# %load q01_cond_prob/build.py
 # So that float division is by default in python 2.7
 from __future__ import division
 
 import pandas as pd
+import numpy as np
+count=0
+countTotal=0
 
 df = pd.read_csv('data/house_pricing.csv')
-
-
-# Enter Code Here
+def cond_prob(df): 
+    Total_OldTown=df[df['Neighborhood']=='OldTown'].shape[0]
+    Total_Houses=df['Neighborhood'].shape[0]
+    Prob1=Total_OldTown/Total_Houses
+    Prob2=(Total_OldTown-1)/(Total_Houses-1)
+    Prob3=(Total_OldTown-2)/(Total_Houses-2)
+    TotalProb=Prob1*Prob2*Prob3
+    return(TotalProb)
 
 
 
diff --git a/q01_cond_prob/tests/__pycache__/__init__.cpython-36.pyc b/q01_cond_prob/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_cond_prob/tests/__pycache__/test_q01_cond_prob.cpython-36.pyc b/q01_cond_prob/tests/__pycache__/test_q01_cond_prob.cpython-36.pyc
diff --git a/q02_confidence_interval/__pycache__/__init__.cpython-36.pyc b/q02_confidence_interval/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_confidence_interval/__pycache__/build.cpython-36.pyc b/q02_confidence_interval/__pycache__/build.cpython-36.pyc
diff --git a/q02_confidence_interval/build.py b/q02_confidence_interval/build.py
@@ -1,13 +1,20 @@
+# %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']
+def confidence_interval(sample): 
+    sample_data=np.random.choice(a=df['GrLivArea'],size=1460)
+    z_critical=stats.norm.ppf(0.95)
+    sigma=sample.std()
+    sample_mean=sample.mean()
+    SE=sigma/math.sqrt(1460)
+    estimate=z_critical*SE
+    confidence_interval=(sample_mean-estimate,sample_mean+estimate)
+    return(confidence_interval)
 
-
-# Write your solution here :
-
-
+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
diff --git a/q02_confidence_interval/tests/__pycache__/test_q02_confidence_interval.cpython-36.pyc b/q02_confidence_interval/tests/__pycache__/test_q02_confidence_interval.cpython-36.pyc
diff --git a/q03_t_test/__pycache__/__init__.cpython-36.pyc b/q03_t_test/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_t_test/__pycache__/build.cpython-36.pyc b/q03_t_test/__pycache__/build.cpython-36.pyc
diff --git a/q03_t_test/build.py b/q03_t_test/build.py
@@ -1,3 +1,4 @@
+# %load q03_t_test/build.py
 # Default imports
 import scipy.stats as stats
 import pandas as pd
@@ -6,4 +7,9 @@
 
 
 # Enter Code Here
+def t_statistic(df):
+    zstat,pval=stats.ttest_1samp(df[df['Neighborhood']=='OldTown']['GrLivArea'],df['GrLivArea'].mean())
+    return(pval,(pval<0.1))
+
+t_statistic(df)
 
diff --git a/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc b/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_t_test/tests/__pycache__/test_q03_t_test.cpython-36.pyc b/q03_t_test/tests/__pycache__/test_q03_t_test.cpython-36.pyc
diff --git a/q04_chi2_test/__pycache__/__init__.cpython-36.pyc b/q04_chi2_test/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_chi2_test/__pycache__/build.cpython-36.pyc b/q04_chi2_test/__pycache__/build.cpython-36.pyc
diff --git a/q04_chi2_test/build.py b/q04_chi2_test/build.py
@@ -1,10 +1,16 @@
+# %load q04_chi2_test/build.py
 # Default imports
 import scipy.stats as stats
 import pandas as pd
 
 df = pd.read_csv('data/house_pricing.csv')
+def chi_square(df):
+    salesdata=pd.qcut(df['SalePrice'],3,labels=['High', 'Medium', 'Low'])
+    p1=pd.Series(salesdata)
+    p2=pd.Series(df['LandSlope'])
+    chi2,pval,dof,expected=stats.chi2_contingency(pd.crosstab(p1,p2))
+    testresult=pval>0.05
+    return(pval,testresult)
 
-
-# Enter Code Here
-
+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
diff --git a/q04_chi2_test/tests/__pycache__/test_q04_chi2_test.cpython-36.pyc b/q04_chi2_test/tests/__pycache__/test_q04_chi2_test.cpython-36.pyc