In [1]:

    

# Chapter 1 - Assignment
import numpy as np
import pandas as pd
# Machine Learning model
from sklearn.naive_bayes import GaussianNB
# Error function
from sklearn.metrics import mean_squared_error


    

In [2]:

    

# Load dataset
iris = pd.read_csv('seaborn-data/iris.csv')


    

In [3]:

    

iris.head()


    

    
Out[3]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
      
species
    
  
  

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
      
setosa
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
      
setosa
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
      
setosa
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
      
setosa
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
      
setosa
    
  

In [4]:

    

# Strip off the labels
X_iris = iris.drop('species', axis=1)
X_iris.shape


    

    
Out[4]:





(150, 4)

In [5]:

    

X_iris.head()


    

    
Out[5]:







  

    

      

      
sepal_length
      
sepal_width
      
petal_length
      
petal_width
    
  
  

    

      
0
      
5.1
      
3.5
      
1.4
      
0.2
    
    

      
1
      
4.9
      
3.0
      
1.4
      
0.2
    
    

      
2
      
4.7
      
3.2
      
1.3
      
0.2
    
    

      
3
      
4.6
      
3.1
      
1.5
      
0.2
    
    

      
4
      
5.0
      
3.6
      
1.4
      
0.2
    
  

In [6]:

    

y_iris = iris['species']
y_iris.shape


    

    
Out[6]:





(150,)

In [7]:

    

y_iris.head()


    

    
Out[7]:





0    setosa
1    setosa
2    setosa
3    setosa
4    setosa
Name: species, dtype: object

In [8]:

    

model = GaussianNB()


    

In [9]:

    

# Fit the model
model.fit(X_iris, y_iris)


    

    
Out[9]:





GaussianNB(priors=None)

In [11]:

    

# Compute the predictions
y_model = model.predict(X_iris)
y_model.shape


    

    
Out[11]:





(150,)

In [13]:

    

hits = (y_iris == y_model)


    

In [14]:

    

hits


    

    
Out[14]:





0       True
1       True
2       True
3       True
4       True
5       True
6       True
7       True
8       True
9       True
10      True
11      True
12      True
13      True
14      True
15      True
16      True
17      True
18      True
19      True
20      True
21      True
22      True
23      True
24      True
25      True
26      True
27      True
28      True
29      True
       ...  
120     True
121     True
122     True
123     True
124     True
125     True
126     True
127     True
128     True
129     True
130     True
131     True
132     True
133    False
134     True
135     True
136     True
137     True
138     True
139     True
140     True
141     True
142     True
143     True
144     True
145     True
146     True
147     True
148     True
149     True
Name: species, Length: 150, dtype: bool

In [16]:

    

y_iris.values


    

    
Out[16]:





array(['setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa',
       'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa',
       'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa',
       'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa',
       'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa',
       'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa',
       'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa',
       'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa',
       'setosa', 'setosa', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'versicolor',
       'versicolor', 'versicolor', 'versicolor', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica', 'virginica', 'virginica',
       'virginica', 'virginica', 'virginica'], dtype=object)

In [20]:

    

# Compute the error
# mean_squared_error(y_iris.values, y_model)
# Should we do it encoding labels?
from sklearn import preprocessing
label_encoder = preprocessing.LabelEncoder()


    

In [21]:

    

# Encode labels
enc_y_iris = label_encoder.fit(y_iris)


    

In [24]:

    

# Show classes
enc_y_iris.classes_


    

    
Out[24]:





array(['setosa', 'versicolor', 'virginica'], dtype=object)

In [ ]:

    

# NOTE - THIS IS LEFT UNEXPLAINED BY THE VIDEOS