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

# # Missing Values Visualizer Examples

# In[1]:


get_ipython().run_line_magic('load_ext', 'autoreload')

get_ipython().run_line_magic('autoreload', '2')

import sys
sys.path.append("./../..")


# In[2]:


get_ipython().run_line_magic('reload_ext', 'yellowbrick')
get_ipython().run_line_magic('matplotlib', 'inline')
# Imports
import pandas as pd  
import numpy as np
import matplotlib.pyplot as plt
import matplotlib
from sklearn.preprocessing import OneHotEncoder
from yellowbrick.contrib.missing import MissingValuesDispersion, MissingValuesBar
from sklearn.datasets import make_classification


# # Use the Horse Colic Data Set 
# 
# Contains natural missing values in data

# In[3]:


headers = pd.read_csv("./horse-colic.attrs")


# In[4]:


url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/horse-colic/horse-colic.data'

# Retrieve Data Set
df = pd.read_csv(url, delim_whitespace=True)
df.columns = headers.Attribute.values
df.replace(to_replace="?", value=np.nan, inplace=True,)


# In[5]:


X = df.drop(['cp_data'], axis=1)
y = df['cp_data']


# # Using Missing Values Dispersion Chart

# In[6]:


classes=['sick', 'healthy']


# ### No target y passed in, produces mono-color chat

# In[7]:


viz = MissingValuesDispersion(classes=classes)
viz.fit(X)
viz.show()


# ### Target y passed in, produces Dispersion chart with elements colored by target variable

# In[8]:


viz = MissingValuesDispersion(classes=classes)
viz.fit(X, y=y)
viz.show()


# # Using Missing Values Bar Chart
# 

# ### No target y passed in, produces mono-color bar chart

# In[9]:


oz = MissingValuesBar(classes=classes)
oz.fit(X)
oz.show()


# ### Target y passed in, produces stacked bar chart

# In[10]:


oz = MissingValuesBar(classes=classes)
oz.fit(X, y=y)
oz.show()


# In[ ]: