diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index 2ba0c81..a6c2d9f 100644 Binary files a/__pycache__/__init__.cpython-36.pyc and b/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_cond_prob/__pycache__/__init__.cpython-36.pyc b/q01_cond_prob/__pycache__/__init__.cpython-36.pyc index a5c1ab2..7df98da 100644 Binary files a/q01_cond_prob/__pycache__/__init__.cpython-36.pyc and b/q01_cond_prob/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_cond_prob/__pycache__/build.cpython-36.pyc b/q01_cond_prob/__pycache__/build.cpython-36.pyc index 4654504..9dfa5a9 100644 Binary files a/q01_cond_prob/__pycache__/build.cpython-36.pyc and b/q01_cond_prob/__pycache__/build.cpython-36.pyc differ diff --git a/q01_cond_prob/build.py b/q01_cond_prob/build.py index 46a16ee..6bff8bc 100644 --- a/q01_cond_prob/build.py +++ b/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 +7,13 @@ df = pd.read_csv('data/house_pricing.csv') + # Enter Code Here +def cond_prob(df): + no_of_houses = len(df) + oldTown_houses = len(df[df['Neighborhood'] ==' OldTown']) + conditional_prob = (oldTown_houses/no_of_houses)*((oldTown_houses-1)/(no_of_houses-1))*((oldTown_houses-2)/(no_of_houses-2)) + return conditional_prob diff --git a/q01_cond_prob/tests/__pycache__/__init__.cpython-36.pyc b/q01_cond_prob/tests/__pycache__/__init__.cpython-36.pyc index 9e8f52b..6c5778d 100644 Binary files a/q01_cond_prob/tests/__pycache__/__init__.cpython-36.pyc and b/q01_cond_prob/tests/__pycache__/__init__.cpython-36.pyc differ 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 index e8852e9..aa08656 100644 Binary files a/q01_cond_prob/tests/__pycache__/test_q01_cond_prob.cpython-36.pyc and b/q01_cond_prob/tests/__pycache__/test_q01_cond_prob.cpython-36.pyc differ diff --git a/q02_confidence_interval/__pycache__/__init__.cpython-36.pyc b/q02_confidence_interval/__pycache__/__init__.cpython-36.pyc index 741ad2d..a3085dc 100644 Binary files a/q02_confidence_interval/__pycache__/__init__.cpython-36.pyc and b/q02_confidence_interval/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_confidence_interval/__pycache__/build.cpython-36.pyc b/q02_confidence_interval/__pycache__/build.cpython-36.pyc index b478df2..5cd11e2 100644 Binary files a/q02_confidence_interval/__pycache__/build.cpython-36.pyc and b/q02_confidence_interval/__pycache__/build.cpython-36.pyc differ diff --git a/q02_confidence_interval/build.py b/q02_confidence_interval/build.py index 023b81e..917a671 100644 --- a/q02_confidence_interval/build.py +++ b/q02_confidence_interval/build.py @@ -1,3 +1,4 @@ +# %load q02_confidence_interval/build.py # Default imports import math import scipy.stats as stats @@ -6,8 +7,23 @@ df = pd.read_csv('data/house_pricing.csv') sample = df['GrLivArea'] +sample.mean() +stats.norm.ppf(q = 0.95) +sample.std() # Write your solution here : +# def confidence_interval(sample): +# sample_mean = sample.mean() +# z_critical = stats.norm.ppf(q = 0.95) +# sam_stdev = sample.std() +# margin_of_error = z_critical * (sam_stdev/math.sqrt(sample.shape[0])) +# confidence_interval = (sample_mean - margin_of_error, +# sample_mean + margin_of_error) +# return confidence_interval + + + + diff --git a/q02_confidence_interval/tests/__pycache__/__init__.cpython-36.pyc b/q02_confidence_interval/tests/__pycache__/__init__.cpython-36.pyc index 2eb0cc4..b98d922 100644 Binary files a/q02_confidence_interval/tests/__pycache__/__init__.cpython-36.pyc and b/q02_confidence_interval/tests/__pycache__/__init__.cpython-36.pyc differ 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 index c3788ca..84bec4f 100644 Binary files a/q02_confidence_interval/tests/__pycache__/test_q02_confidence_interval.cpython-36.pyc and b/q02_confidence_interval/tests/__pycache__/test_q02_confidence_interval.cpython-36.pyc differ diff --git a/q03_t_test/__pycache__/__init__.cpython-36.pyc b/q03_t_test/__pycache__/__init__.cpython-36.pyc index cac7d29..35e19f3 100644 Binary files a/q03_t_test/__pycache__/__init__.cpython-36.pyc and b/q03_t_test/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_t_test/__pycache__/build.cpython-36.pyc b/q03_t_test/__pycache__/build.cpython-36.pyc index d55dfcf..9596ce3 100644 Binary files a/q03_t_test/__pycache__/build.cpython-36.pyc and b/q03_t_test/__pycache__/build.cpython-36.pyc differ diff --git a/q03_t_test/build.py b/q03_t_test/build.py index f966b62..5d75940 100644 --- 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 @@ -7,3 +8,10 @@ # Enter Code Here +def t_statistic(df): + stat,p_value = stats.ttest_1samp(a = df[df['Neighborhood'] == 'OldTown']['GrLivArea'],popmean= df['GrLivArea'].mean()) + test_result = stats.norm.ppf(.90) + return p_value,p_value > test_result + + + diff --git a/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc b/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc index c489290..eba27a9 100644 Binary files a/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc and b/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc differ 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 index ffd3551..f2af9b8 100644 Binary files a/q03_t_test/tests/__pycache__/test_q03_t_test.cpython-36.pyc and b/q03_t_test/tests/__pycache__/test_q03_t_test.cpython-36.pyc differ diff --git a/q04_chi2_test/__pycache__/__init__.cpython-36.pyc b/q04_chi2_test/__pycache__/__init__.cpython-36.pyc index 07afcf0..959645a 100644 Binary files a/q04_chi2_test/__pycache__/__init__.cpython-36.pyc and b/q04_chi2_test/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_chi2_test/__pycache__/build.cpython-36.pyc b/q04_chi2_test/__pycache__/build.cpython-36.pyc index 699bd6a..dafb610 100644 Binary files a/q04_chi2_test/__pycache__/build.cpython-36.pyc and b/q04_chi2_test/__pycache__/build.cpython-36.pyc differ diff --git a/q04_chi2_test/build.py b/q04_chi2_test/build.py index 4f20455..70bd1c2 100644 --- a/q04_chi2_test/build.py +++ b/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 @@ -7,4 +8,11 @@ # Enter Code Here +def chi_square(df): + price = pd.qcut(df['SalePrice'], 3, labels = ['High', 'Medium', 'Low']) + freqtab = pd.crosstab(df.LandSlope, price) + chi2,pval,dof,expected = stats.chi2_contingency(freqtab) + return pval, pval>0.5 + + diff --git a/q04_chi2_test/tests/__pycache__/__init__.cpython-36.pyc b/q04_chi2_test/tests/__pycache__/__init__.cpython-36.pyc index 45a1b92..b65adba 100644 Binary files a/q04_chi2_test/tests/__pycache__/__init__.cpython-36.pyc and b/q04_chi2_test/tests/__pycache__/__init__.cpython-36.pyc differ 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 index b2a8c04..6feb546 100644 Binary files a/q04_chi2_test/tests/__pycache__/test_q04_chi2_test.cpython-36.pyc and b/q04_chi2_test/tests/__pycache__/test_q04_chi2_test.cpython-36.pyc differ