commit-live-students · Abhimanyu22 · Oct 13, 2018 · Oct 13, 2018 · Oct 13, 2018 · Oct 13, 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 +1,20 @@
-# So that float division is by default in python 2.7
 from __future__ import division
-
 import pandas as pd
 
 df = pd.read_csv('data/house_pricing.csv')
 
+def cond_prob(df):
+    allhouses = df.shape[0]
+    houses_in_OldTown = df[df['Neighborhood'] == 'OldTown'].shape[0]
+    n = (houses_in_OldTown)*(houses_in_OldTown-1)*(houses_in_OldTown-2)
+    k = ( allhouses)*(allhouses-1)*(allhouses-2)
+    probofthree = float(n/k)
+
+    return probofthree
+
+cond_prob(df)
+
 
-# Enter Code Here
 
 
 
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 +1,31 @@
-# 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']
+z_critical = stats.norm.ppf(q = 0.95)
+
+def confidence_interval(sample):
+    sample_mean = sample.mean()
+    samplestd = sample.std()
+    n = np.size(sample)
+    stderror = samplestd/(n**(1/2))
+    marginerror = z_critical*stderror
+    lower = sample_mean - marginerror
+    upper = sample_mean + marginerror
+
+    return lower, upper
+
+confidence_interval(sample)
+
+
+
+
+
 
 
-# Write your solution here :
 
 
 
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
@@ -1,9 +1,18 @@
-# Default imports
 import scipy.stats as stats
 import pandas as pd
+import numpy as np
 
 df = pd.read_csv('data/house_pricing.csv')
 
+def t_statistic(df):
+    t_statistic, p_value = stats.ttest_1samp(a= df[df['Neighborhood'] == 'OldTown']['GrLivArea'],              
+                 popmean= df['GrLivArea'].mean())
+    t_critical = stats.t.ppf(1-0.1,df[df['Neighborhood'] == 'OldTown']['GrLivArea'].shape[0])
+    test_result = p_value>t_critical
+
+    return p_value, test_result
+
+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
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 +1,19 @@
-# Default imports
 import scipy.stats as stats
 import pandas as pd
 
+
 df = pd.read_csv('data/house_pricing.csv')
 
+def chi_square(df):
+    lsdf = df['LandSlope']
+    catdf = pd.qcut(df['SalePrice'], 3, labels = ['High','Med','Low'], retbins= False)
+    freqtab=pd.crosstab(df['LandSlope'],catdf)
+    chi2,p_value,dof,expected = stats.chi2_contingency(freqtab)
+    test_result=(p_value<0.05)
+    print(freqtab)
+
+    return p_value, test_result
 
-# 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