In [7]:
import pandas as df
import numpy as np
from sklearn import tree
from sklearn.tree import DecisionTreeClassifier
import matplotlib.pyplot as plt
In [60]:
data=df.read_csv('user.csv')
In [33]:
print(data)

    Age  Experience  Rank Nationality   Go
0    36          10     9          UK   NO
1    42          12     4         USA   NO
2    23           4     6           N   NO
3    52           4     4         USA   NO
4    43          21     8         USA  YES
5    44          14     5          UK   NO
6    66           3     7           N  YES
7    35          14     9          UK  YES
8    52          13     7           N  YES
9    35           5     9           N  YES
10   24           3     5         USA   NO
11   18           3     7          UK  YES
12   45           9     9          UK  YES
In [61]:
print(data)

    Age  Experience  Rank Nationality   Go
0    36          10     9          UK   NO
1    42          12     4         USA   NO
2    23           4     6           N   NO
3    52           4     4         USA   NO
4    43          21     8         USA  YES
5    44          14     5          UK   NO
6    66           3     7           N  YES
7    35          14     9          UK  YES
8    52          13     7           N  YES
9    35           5     9           N  YES
10   24           3     5         USA   NO
11   18           3     7          UK  YES
12   45           9     9          UK  YES
In [62]:
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 13 entries, 0 to 12
Data columns (total 5 columns):
 #   Column       Non-Null Count  Dtype 
---  ------       --------------  ----- 
 0   Age          13 non-null     int64 
 1   Experience   13 non-null     int64 
 2   Rank         13 non-null     int64 
 3   Nationality  13 non-null     object
 4   Go           13 non-null     object
dtypes: int64(3), object(2)
memory usage: 652.0+ bytes
In [63]:
d = {'UK': 0, 'USA': 1, 'N': 2}
data['Nationality'] = data['Nationality'].map(d)
d = {'YES': 1, 'NO': 0}
data['Go'] = data['Go'].map(d)
In [64]:
print(data)

    Age  Experience  Rank  Nationality  Go
0    36          10     9            0   0
1    42          12     4            1   0
2    23           4     6            2   0
3    52           4     4            1   0
4    43          21     8            1   1
5    44          14     5            0   0
6    66           3     7            2   1
7    35          14     9            0   1
8    52          13     7            2   1
9    35           5     9            2   1
10   24           3     5            1   0
11   18           3     7            0   1
12   45           9     9            0   1
In [65]:
features=['Age','Experience','Rank','Nationality']
In [66]:
X=data[features]
In [78]:
Y=data['Go']
In [84]:
dtree=DecisionTreeClassifier()
In [85]:
dtree=dtree.fit(X, Y)
In [93]:
plt.figure(figsize=(10, 8))
tree.plot_tree(dtree,feature_names=features,   filled=True, 
          rounded=True)
Out[93]:
[Text(0.2857142857142857, 0.9, 'Rank <= 6.5\ngini = 0.497\nsamples = 13\nvalue = [6, 7]'),
 Text(0.14285714285714285, 0.7, 'gini = 0.0\nsamples = 5\nvalue = [5, 0]'),
 Text(0.42857142857142855, 0.7, 'Rank <= 8.5\ngini = 0.219\nsamples = 8\nvalue = [1, 7]'),
 Text(0.2857142857142857, 0.5, 'gini = 0.0\nsamples = 4\nvalue = [0, 4]'),
 Text(0.5714285714285714, 0.5, 'Experience <= 9.5\ngini = 0.375\nsamples = 4\nvalue = [1, 3]'),
 Text(0.42857142857142855, 0.3, 'gini = 0.0\nsamples = 2\nvalue = [0, 2]'),
 Text(0.7142857142857143, 0.3, 'Age <= 35.5\ngini = 0.5\nsamples = 2\nvalue = [1, 1]'),
 Text(0.5714285714285714, 0.1, 'gini = 0.0\nsamples = 1\nvalue = [0, 1]'),
 Text(0.8571428571428571, 0.1, 'gini = 0.0\nsamples = 1\nvalue = [1, 0]')]
In [95]:
print(dtree.predict([[40, 7, 8, 1]]))

[1]

C:\Users\seena.joseph\AppData\Local\anaconda3\Lib\site-packages\sklearn\base.py:464: UserWarning: X does not have valid feature names, but DecisionTreeClassifier was fitted with feature names
  warnings.warn(
In [ ]: