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
 
@@ -6,7 +7,18 @@
 df = pd.read_csv('data/house_pricing.csv')
 
 
-# Enter Code Here
 
+def cond_prob(df):
+
+    # number of ho
+    total_house_in_oldtown = len(df[df['Neighborhood']== 'OldTown']) # number of house in oldtown
+    total_house = len(df)  # total number of house
+
+    #calculate conditional probability 
+    cond_probability = ((total_house_in_oldtown)/(total_house))*((total_house_in_oldtown-1)/(total_house-1)) * ((total_house_in_oldtown-2)/(total_house-2))
+
+    return cond_probability
+
+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
@@ -8,6 +9,19 @@
 
 
 # Write your solution here :
+def confidence_interval(df):
+
+    sample_mean= sample.mean() #find the mean of sample
+    z_critical = stats.norm.ppf(0.95)  # z-value
+    sample_dev = sample.std() # stardard deviation of sample
+    standard_error = z_critical * (sample_dev/(len(sample))**0.5) #standa
+    lower_limit = sample_mean - standard_error
+    upper_limit = sample_mean + standard_error
+
+    return lower_limit, upper_limit
 
 
 
+confidence_interval(df)
+
+

q03_t_test/build.py

@@ -1,9 +1,31 @@
+# %load q03_t_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')
 
+def t_statistic(df):
+    # Enter Code Here
+    # alpha 0.05 for 95% significance level, its means 5% risk 
+    # alpha 0.10 for 90% significance level, its means 10% risk
+    alpha = 0.10
+    t_test, p_value = stats.ttest_1samp(df[df['Neighborhood' ]=='OldTown']['GrLivArea'], df['GrLivArea'].mean())
+
+    if p_value < alpha:
+
+        return  p_value, np.bool_(True)
+    else:
+
+         return  p_value, np.bool_(False)
+
+
+t_statistic(df)
+
+
+
+
+
 
-# Enter Code Here
 

q04_chi2_test/build.py

@@ -1,10 +1,30 @@
+# %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
+def chi_square(df):
+
+    #price converted into catogrical on basic of quantile
+    price = pd.qcut(df['SalePrice'],3, labels =['low', 'medium', 'High'])
+
+    #contingency table group variable to show correlation between two varable
+    freq_table = pd.crosstab(df.LandSlope, price)
+
+    #calculting chi and p value from 
+    chi, p, dof, expected = stats.chi2_contingency(freq_table)
+
+    if p < 0.05: # if value of p is very low than variable are independent
+        return p, np.bool_(True)
+    else:
+        return p, np.bool_(False) #else not independent
+
+chi_square(df)
+