#!/usr/bin/env python
# coding: utf-8

# In[2]:


get_ipython().run_line_magic('matplotlib', 'inline')


# # Empirical Cumulative Distribution Function Plot

# A function to conveniently plot an empirical cumulative distribution function. 

# > from mlxtend.ecdf import ecdf

# ## Overview

# A function to conveniently plot an empirical cumulative distribution function (ECDF) and adding percentile thresholds for exploratory data analysis.

# ### References
# 
# - -

# ## Example 1 - ECDF

# In[3]:


from mlxtend.data import iris_data
from mlxtend.plotting import ecdf
import matplotlib.pyplot as plt

X, y = iris_data()

ax, _, _ = ecdf(x=X[:, 0], x_label='sepal length (cm)')
plt.show()


# ## Example 2 - Multiple ECDFs

# In[5]:


from mlxtend.data import iris_data
from mlxtend.plotting import ecdf
import matplotlib.pyplot as plt

X, y = iris_data()

# first ecdf
x1 = X[:, 0]
ax, _, _ = ecdf(x1, x_label='cm')

# second ecdf
x2 = X[:, 1]
ax, _, _ = ecdf(x2, ax=ax)

plt.legend(['sepal length', 'sepal width'])
plt.show()


# ## Example 3 - ECDF with Percentile Thresholds

# In[7]:


from mlxtend.data import iris_data
from mlxtend.plotting import ecdf
import matplotlib.pyplot as plt

X, y = iris_data()

ax, threshold, count = ecdf(x=X[:, 0], 
                            x_label='sepal length (cm)',
                            percentile=0.8)

plt.show()

print('Feature threshold at the 80th percentile:', threshold)
print('Number of samples below the threshold:', count)


# ## API

# In[1]:


with open('../../api_modules/mlxtend.plotting/ecdf.md', 'r') as f:
    print(f.read())