Commit Live PR

q01_cond_prob/build.py

@@ -1,3 +1,4 @@
+# %load q01_cond_prob/build.py
 # So that float division is by default in python 2.7
 from __future__ import division
 
@@ -7,6 +8,16 @@
 
 
 # Enter Code Here
+def cond_prob(data):
+    all_houses = data.shape[0]
+    houses_in_OldTown = data[data['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 float(conditional_prob)
+
+cond_prob(df)
+
+
+
 
 
 

q02_confidence_interval/build.py

@@ -1,3 +1,4 @@
+# %load q02_confidence_interval/build.py
 # Default imports
 import math
 import scipy.stats as stats
@@ -10,4 +11,23 @@
 # Write your solution here :
 
 
+def confidence_interval(sample):
+    sample_size= sample.size
+    pop_mean=sample.mean()
+    z_critical = stats.norm.ppf(q = 0.95)  # Get the z-critical value*
+
+#     print('z-critical value:')              # Check the z-critical value
+#     print(z_critical)                        
+
+    pop_stdev = sample.std()  # Get the population standard deviation
+
+    margin_of_error = z_critical * (pop_stdev/math.sqrt(sample_size))
+
+    lower_limit = pop_mean - margin_of_error
+    upper_limit = pop_mean + margin_of_error
+    return float(lower_limit),float(upper_limit)
+confidence_interval(sample)
+
+
+
 

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 +7,18 @@
 
 
 # Enter Code Here
+from statsmodels.stats.weightstats import ztest
+def t_statistic(df):
+    deg_freedom = df['Neighborhood'].value_counts()['OldTown']-1
+    p=0.90
+    value = t.ppf(p, deg_freedom)
+#     result=t_statistics(0.90,deg_freedom)
+    result,p_value =stats.ttest_1samp(a= df[df['Neighborhood'] == 'OldTown']['GrLivArea'], popmean= df['GrLivArea'].mean())
+    test_result=result>value
+    return float(p_value),test_result
+
+t_statistic(df)
+
+
+
 

q04_chi2_test/build.py

@@ -1,3 +1,4 @@
+# %load q04_chi2_test/build.py
 # Default imports
 import scipy.stats as stats
 import pandas as pd
@@ -8,3 +9,18 @@
 # Enter Code Here
 
 
+def chi_square(data):
+    x = data.LandSlope
+    y = pd.qcut(data['SalePrice'], 3, labels = ['High', 'Medium', 'Low'])
+
+    freqtable = pd.crosstab(x,y)
+    chi2,pval,dof,expected = stats.chi2_contingency(freqtable)
+    crit = stats.chi2.ppf(q = 0.95, df = dof)
+    test_result = crit < chi2
+
+    return pval , test_result
+
+chi_square(df)
+
+
+