from google.

colab import drive

drive.mount('/content/drive')

Mounted at /content/drive

from google.colab import files

uploaded = files.upload()

Choose Files No file chosen Upload widget is only available when the cell has been executed in the current browser session. Please rerun this cell to
enable.
Saving iris.csv to iris.csv

import pandas as pd
iris = pd.read_csv('/content/iris.csv')

from matplotlib import pyplot as plt

import numpy as np
iris

output sepal.length sepal.width petal.length petal.width variety

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

... ... ... ... ... ...

145 6.7 3.0 5.2 2.3 Virginica

146 6.3 2.5 5.0 1.9 Virginica

147 6.5 3.0 5.2 2.0 Virginica

148 6.2 3.4 5.4 2.3 Virginica

149 5.9 3.0 5.1 1.8 Virginica

150 rows × 5 columns

iris.shape

(150, 5)

iris.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 5 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 sepal.length 150 non-null float64
1 sepal.width 150 non-null float64
2 petal.length 150 non-null float64
3 petal.width 150 non-null float64
4 variety 150 non-null object
dtypes: float64(4), object(1)
memory usage: 6.0+ KB

X = iris.iloc[ : , 0:4]
X
 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

... ... ... ... ...

145 6.7 3.0 5.2 2.3

146 6.3 2.5 5.0 1.9

147 6.5 3.0 5.2 2.0

148 6.2 3.4 5.4 2.3

149 5.9 3.0 5.1 1.8

150 rows × 4 columns

Y = iris.iloc[ : , 4: ]
Y.variety.unique()

array(['Setosa', 'Versicolor', 'Virginica'], dtype=object)

from sklearn.model_selection import train_test_split

X_train, X_test, Y_train, Y_test = train_test_split(X , Y, test_size = 0.25, random_state = 5)

X_train

sepal.length sepal.width petal.length petal.width

40 5.0 3.5 1.3 0.3

115 6.4 3.2 5.3 2.3

142 5.8 2.7 5.1 1.9

69 5.6 2.5 3.9 1.1

17 5.1 3.5 1.4 0.3

... ... ... ... ...

8 4.4 2.9 1.4 0.2

73 6.1 2.8 4.7 1.2

144 6.7 3.3 5.7 2.5

118 7.7 2.6 6.9 2.3

99 5.7 2.8 4.1 1.3

112 rows × 4 columns

from sklearn.tree import DecisionTreeClassifier

clf = DecisionTreeClassifier(random_state = 1234, criterion = 'entropy')

clf.fit(X_train , Y_train)

▾ DecisionTreeClassifier
DecisionTreeClassifier(criterion='entropy', random_state=1234)

from sklearn import tree

text_representation = tree.export_text(clf)

print(text_representation)

|--- feature_2 <= 2.45

| |--- class: Setosa
|--- feature_2 > 2.45
| |--- feature_3 <= 1.75
| | |--- feature_3 <= 1.45
| | | |--- class: Versicolor
| | |--- feature_3 > 1.45
| | | |--- feature_1 <= 2.60
| | | | |--- feature_0 <= 6.10
| | | | | |--- class: Virginica
| | | | |--- feature_0 > 6.10
 | | | | | |--- class: Versicolor
| | | |--- feature_1 > 2.60
| | | | |--- feature_0 <= 7.05
| | | | | |--- class: Versicolor
| | | | |--- feature_0 > 7.05
| | | | | |--- class: Virginica
| |--- feature_3 > 1.75
| | |--- class: Virginica

fig = plt.figure(figsize = (25 , 20) , dpi = 200.0)

_ = tree.plot_tree(clf,
feature_names = ['sepal.length' ,'sepal.width', 'petal.length', 'petal.width'],
class_names = ['setosa', 'versicolor', 'virginica'],
filled = True)
from sklearn.metrics import accuracy_score

pred_train = clf.predict(X_train)

accuracy_train = accuracy_score(Y_train, pred_train)

print('% of Accuracy on training data: ', accuracy_train * 100 )

# Let us test the accuracy of the model on the test data (or new data or unseen data).

pred_test = clf.predict(X_test)

accuracy_test = accuracy_score(Y_test, pred_test)

print('% of Accuracy on test data: ', accuracy_test * 100 )

% of Accuracy on training data: 100.0

% of Accuracy on test data: 92.10526315789474

Double-click (or enter) to edit

new_data = {'sepal.length' : [3.7],

'sepal.width' : [3.0],
'petal.length' : [2.2],
'petal.width' : [1.3] }

new_df = pd.DataFrame(new_data)

new_df.head()

sepal.length sepal.width petal.length petal.width

0 3.7 3.0 2.2 1.3