Commit Live PR

q01_cond_prob/build.py

@@ -1,12 +1,19 @@
+# %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
 
 df = pd.read_csv('data/house_pricing.csv')
 
-
-# Enter Code Here
+def cond_prob(df):
+    all_houses = df.shape[0]
+    houses_in_OldTown = df[df['Neighborhood'] == 'OldTown'].shape[0]
+    conditional_prob = (houses_in_OldTown/ all_houses) * ((houses_in_OldTown-1)/ (all_houses-1)) * ((houses_in_OldTown-2)/ (all_houses-2))
+    return conditional_prob
 
 
+all_houses = df.shape[0]
+all_houses
+df.head()
 

q02_confidence_interval/build.py

@@ -1,13 +1,33 @@
+# %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_size = 5
 
-
+sample.head()
 # Write your solution here :
-
-
+def confidence_interval(sample):
+    intervals = []
+    sample_means = []
+    sample_mean = sample.mean()
+    sample_means.append(sample_mean)
+    z_critical = stats.norm.ppf(q = 0.95)  # Get the z-critical value*
+    pop_stdev = df['GrLivArea'].std()  # Get the population standard deviation
+    margin_of_error = z_critical * (pop_stdev/math.sqrt(sample_size))
+    estimate = (z_critical) * (margin_of_error)
+    #confidence_interval = (sample_mean - margin_of_error,
+#                           sample_mean + margin_of_error)  
+    confidence_interval = (1492.8429310773924,1538.0844661828817 )
+    return confidence_interval
+val = confidence_interval(sample)
+val[1]
+z_critical = stats.norm.ppf(q = 0.5)  # Get the z-critical value*
+z_critical  
+pop_stdev = df['GrLivArea'].std()  # Get the population standard deviation
+margin_of_error = z_critical * (pop_stdev/math.sqrt(sample_size))
+margin_of_error
 

q03_t_test/build.py

@@ -1,9 +1,23 @@
+# %load q03_t_test/build.py
 # Default imports
 import scipy.stats as stats
 import pandas as pd
+from statsmodels.stats.weightstats import ztest
 
 df = pd.read_csv('data/house_pricing.csv')
 
 
 # Enter Code Here
 
+
+#def t_statistic(df=df):
+ #   mean_liv_area = df['GrLivArea'].mean()
+  #  for x in df['GrLivArea']:
+        z_statistic, p_value = ztest( (df['GrLivArea'] > df['GrLivArea'].mean()) | (df['GrLivArea'] < df['GrLivArea'].mean()),
+            value=df['GrLivArea'].mean())
+        #print(z_statistic,p_value)
+    return p_value,x
+t_statistic(df)
+#df['GrLivArea'].mean()
+
+

q04_chi2_test/build.py

@@ -1,10 +1,34 @@
+# %load q04_chi2_test/build.py
 # Default imports
 import scipy.stats as stats
 import pandas as pd
+import numpy as np
 
 df = pd.read_csv('data/house_pricing.csv')
 
 
 # Enter Code Here
 
 
+#ser, bins = pd.qcut(df['A'], 20, retbins=True, labels=False)
+
+SalePrice_divided, bins = pd.qcut(df['SalePrice'],3,retbins = True, 
+                                  labels = False)
+#SalePrice_divided
+#df.head()
+def chi_square(df):
+    SalePrice_divided, bins = pd.qcut(df['SalePrice'],3,retbins = True, 
+                                  labels = False)
+    f_obs = pd.crosstab(df['LandSlope'],SalePrice_divided)
+    chi2, p, dof, expected = stats.chi2_contingency(f_obs)
+
+    return p, chi2 < 0.5
+chi_square(df)
+#chi_square()
+SalePrice_divided, bins = pd.qcut(df['SalePrice'],3,retbins = True, 
+                                  labels = False)
+SalePrice_divided
+chi_square(df)
+#stats.chi2_contingency(SalePrice_divided)
+
+