def test_SquareTable_from_data():
np.random.seed(434)
df = pd.DataFrame(index=range(100), columns=["v1", "v2"])
df["v1"] = np.random.randint(0, 5, 100)
df["v2"] = np.random.randint(0, 5, 100)
table = pd.crosstab(df["v1"], df["v2"])
rslt1 = ctab.SquareTable(table)
rslt2 = ctab.SquareTable.from_data(df)
rslt3 = ctab.SquareTable(np.asarray(table))
assert_equal(rslt1.summary().as_text(), rslt2.summary().as_text())
assert_equal(rslt2.summary().as_text(), rslt3.summary().as_text())
def core(tsx, tsy):
'''
input
--------
tsx: 定类型数据
tsy: 定类型数据
'''
crosstab = pd.crosstab(tsx, tsy)
crosstab2 = pd.crosstab(tsx, tsy, margins=True)
crosstab2 = crosstab2.rename(columns={'All': '总计'}, index={'All': '总计'})
if crosstab.shape == (2, 2):
res = contingency_tables.mcnemar(crosstab)
method = 'mcnemar'
else:
res = contingency_tables.SquareTable(crosstab).symmetry(
method="bowker")
method = 'bowker'
chi2 = res.statistic
p = res.pvalue
expected = stats.contingency.expected_freq(crosstab)
dfe = pd.DataFrame(expected, columns=tsy.unique(),
index=tsx.unique()).round(3)
dfte = crosstab.astype(str) + ' (' + dfe.astype(str) + ')'
dfte['总计'] = crosstab2['总计']
dfte.loc['总计'] = crosstab2.loc['总计']
dfte['检验方法'] = method
dfte['卡方统计量'] = chi2
dfte['p-值'] = p
dfte.index.name = '类别'
return dfte.reset_index().set_index(['检验方法', '卡方统计量', 'p-值', '类别'])
def test_SquareTable_from_data():
np.random.seed(434)
df = pd.DataFrame(index=range(100), columns=["v1", "v2"])
df["v1"] = np.random.randint(0, 5, 100)
df["v2"] = np.random.randint(0, 5, 100)
table = pd.crosstab(df["v1"], df["v2"])
rslt1 = ctab.SquareTable(table)
rslt2 = ctab.SquareTable.from_data(df)
rslt3 = ctab.SquareTable(np.asarray(table))
assert_equal(rslt1.summary().as_text(), rslt2.summary().as_text())
assert_equal(rslt2.summary().as_text(), rslt3.summary().as_text())
s = str(rslt1)
assert_equal(s.startswith('A 5x5 contingency table with counts:'), True)
assert_equal(rslt1.table[0, 0], 8.)
def test_SquareTable_nonsquare():
tab = [[1, 0, 3], [2, 1, 4], [3, 0, 5]]
df = pd.DataFrame(tab, index=[0, 1, 3], columns=[0, 2, 3])
df2 = ctab.SquareTable(df, shift_zeros=False)
e = np.asarray([[1, 0, 0, 3], [2, 0, 1, 4], [0, 0, 0, 0], [3, 0, 0, 5]],
dtype=np.float64)
assert_equal(e, df2.table)