from kcbo import lognormal_comparison_test, t_test, conversion_test

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns
%matplotlib inline

# Generate some data
g1d = np.random.lognormal(mean=3, sigma=1, size=10000)
g1l = ['A'] * g1d.shape[0]
g2d = np.random.lognormal(mean=3.03, sigma=1, size=10000)
g2l = ['B'] * g2d.shape[0]

g1 = pd.DataFrame(data=g1d, columns=['value'])
g1['group'] = g1l
g2 = pd.DataFrame(data=g2d, columns=['value'])
g2['group'] = g2l

lognormal_data = pd.concat([g1, g2])

summary, data = lognormal_comparison_test(lognormal_data, samples=100000)

print summary

A,B = data['A']['median'], data['B']['median']
diff = data[('A','B')]['diff_medians']

f, axes = plt.subplots(1,2, figsize=(12, 7))
sns.set(style="white", palette="muted")
sns.despine(left=True)

sns.distplot(A, ax=axes[0], label='Median Estimate Density for A')
sns.distplot(B, ax=axes[0], label='Median Estimate Density for B')
sns.distplot(diff, ax=axes[1], label='Difference of Densities (B-A)')

axes[0].legend()
axes[1].legend()

plt.show()

n1,n2 = (140,200)

group1 = np.random.normal(15,2,n1)
group2 = np.random.normal(15.7,2,n2)

A = zip(['A']*n1, group1)
B = zip(['B']*n2, group2)

df = pd.concat([pd.DataFrame(A), pd.DataFrame(B)])
df.columns = 'group','value'
df.head()

description, data = t_test(df,groupcol='group',valuecol='value',  samples=60000, progress_bar=True)

print description

diff = data[('A', 'B')]['diff_means']

f, axes = plt.subplots(1,1, figsize=(12, 7))
sns.despine(left=True)
sns.distplot(diff, label='Difference of Means').legend()
plt.show()

A = {'group':'A', 'trials': 10000, 'successes':5000}
B = {'group':'B', 'trials': 8000, 'successes':4090}

df = pd.DataFrame([A,B])
df

summary, data = conversion_test(df, groupcol='group',successcol='successes',totalcol='trials')

print summary

A = data['A']['distribution']
B = data['B']['distribution']
diff = data[('A','B')]['distribution']

f, axes = plt.subplots(1,2, figsize=(12, 7))
sns.set(style="white", palette="muted")
sns.despine(left=True)

sns.distplot(A, ax=axes[0], label='Density Estimate for A')
sns.distplot(B, ax=axes[0], label='Density Estimate for B')
sns.distplot(diff, ax=axes[1], label='Difference of Densities (B-A)')

axes[0].legend()
axes[1].legend()

plt.show()