diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index 2ba0c81..15feb20 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..2262f2d 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..fa52d7f 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..dbbb147 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 @@ -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) + + + diff --git a/q01_cond_prob/tests/__pycache__/__init__.cpython-36.pyc b/q01_cond_prob/tests/__pycache__/__init__.cpython-36.pyc index 9e8f52b..8f2d8df 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..f7a81a1 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..23abe86 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..3ab3713 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..7e077f3 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 @@ -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) + + + diff --git a/q02_confidence_interval/tests/__pycache__/__init__.cpython-36.pyc b/q02_confidence_interval/tests/__pycache__/__init__.cpython-36.pyc index 2eb0cc4..8b1a1ce 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..a4844b8 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..0de83d5 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..ca8f5ab 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..fe25082 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 @@ -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) + + + diff --git a/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc b/q03_t_test/tests/__pycache__/__init__.cpython-36.pyc index c489290..a10f2a3 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..7bd3fed 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..ea427e2 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..2fd7f98 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..7eb3738 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 @@ -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) + + + diff --git a/q04_chi2_test/tests/__pycache__/__init__.cpython-36.pyc b/q04_chi2_test/tests/__pycache__/__init__.cpython-36.pyc index 45a1b92..3088fa9 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..75d89b2 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