def test_binary_binary():
"""
Tests binary-binary.
:return: None.
"""
get_data = lambda x, y, n: [(x, y) for _ in range(n)]
data = get_data(1, 1, 207) + get_data(1, 0, 282) + get_data(0, 1, 231) + get_data(0, 0, 242)
a = [a for a, _ in data]
b = [b for _, b in data]
for m in BinaryTable.measures():
r = binary_binary(a, b, m)
print(f'{r}: {m}')
from pypair.association import binary_binary
from pypair.contingency import BinaryTable
get_data = lambda x, y, n: [(x, y) for _ in range(n)]
data = get_data(1, 1, 207) + get_data(1, 0, 282) + get_data(
0, 1, 231) + get_data(0, 0, 242)
a = [a for a, _ in data]
b = [b for _, b in data]
for m in BinaryTable.measures():
r = binary_binary(a, b, m)
print(f'{r}: {m}')
print('-' * 15)
table = BinaryTable(a, b)
for m in table.measures():
r = table.get(m)
print(f'{r}: {m}')
from random import randint
import pandas as pd
from pypair.association import binary_binary
from pypair.util import corr
def get_data(n_rows=1000, n_cols=5):
data = [
tuple([randint(0, 1) for _ in range(n_cols)]) for _ in range(n_rows)
]
cols = [f'x{i}' for i in range(n_cols)]
return pd.DataFrame(data, columns=cols)
if __name__ == '__main__':
jaccard = lambda a, b: binary_binary(a, b, measure='jaccard')
tanimoto = lambda a, b: binary_binary(a, b, measure='tanimoto_i')
df = get_data()
jaccard_corr = corr(df, jaccard)
tanimoto_corr = corr(df, tanimoto)
print(jaccard_corr)
print('-' * 15)
print(tanimoto_corr)
def plot_colinearity_variations(df):
from pypair.association import binary_binary
jaccard = lambda a, b: binary_binary(a, b, measure="jaccard")
tanimoto = lambda a, b: binary_binary(a, b, measure="tanimoto_i")
# This measure is typically used to judge the similarity between two clusters.
ochiai = lambda a, b: binary_binary(a, b, measure="ochia_i")
# Yule's Q is based off of the odds ratio or cross-product ratio, a measure of proportional reduction in error (PRE)
yule = lambda a, b: binary_binary(a, b, measure="yule_q")
# A higher mutual information value implies strong association
m_inf = lambda a, b: binary_binary(a, b, measure="mutual_information")
# Tetrachoric correlation ranges from :math:`[-1, 1]`, where 0 indicates no agreement,
# 1 indicates perfect agreement and -1 indicates perfect disagreement.
tetrachoric = lambda a, b: binary_binary(a, b, measure="tetrachoric")
train_df = pd_scale_norm_df(df)
# Identify collinearity between columns¶
fig = plt.figure(figsize=(20, 15))
corr_df_1 = train_df.corr(method="pearson")
ax = fig.add_subplot(3, 3, 1)
ax.title.set_text("collinearity, Pearson similarity measure: ")
sns.heatmap(corr_df_1, ax=ax, cmap="RdYlBu")
corr_df_2 = train_df.corr(method="spearman")
ax = fig.add_subplot(3, 3, 2)
ax.title.set_text("Spearman similarity measure: ")
sns.heatmap(corr_df_2, ax=ax, cmap="RdYlBu")
corr_df_3 = train_df.corr(method=histogram_intersection)
ax = fig.add_subplot(3, 3, 3)
ax.title.set_text(
"collinearity, Histogram Intersection similarity measure: ")
sns.heatmap(corr_df_3, ax=ax, cmap="RdYlBu")
corr_df_4 = train_df.corr(method=jaccard)
ax = fig.add_subplot(3, 3, 4)
ax.title.set_text("Jaccard similarity measure: ")
sns.heatmap(corr_df_4, ax=ax, cmap="RdYlBu")
corr_df_5 = train_df.corr(method=tanimoto)
ax = fig.add_subplot(3, 3, 5)
ax.title.set_text("Tanimoto similarity measure (Jaccard Index): ")
sns.heatmap(corr_df_5, ax=ax, cmap="RdYlBu")
corr_df_6 = train_df.corr(method=ochiai)
ax = fig.add_subplot(3, 3, 6)
ax.title.set_text("Ochiai similarity measure (cosine similarity): ")
sns.heatmap(corr_df_6, ax=ax, cmap="RdYlBu")
corr_df_7 = train_df.corr(method=yule)
ax = fig.add_subplot(3, 3, 7)
ax.title.set_text("yule Q measure (cosine similarity): ")
sns.heatmap(corr_df_7, ax=ax, cmap="RdYlBu")
corr_df_8 = train_df.corr(method=m_inf)
ax = fig.add_subplot(3, 3, 8)
ax.title.set_text("Mutual Information: ")
sns.heatmap(corr_df_8, ax=ax, cmap="RdYlBu")
corr_df_9 = train_df.corr(method=tetrachoric)
ax = fig.add_subplot(3, 3, 9)
ax.title.set_text("tetrachoric correlation: ")
sns.heatmap(corr_df_9, ax=ax, cmap="RdYlBu")
fig.tight_layout()
return fig
def compute(a, b, df):
x = df[a]
y = df[b]
return f'{a}_{b}', binary_binary(x, y, measure='jaccard')