by Jesse Grootjen
The material is licensed under the Creative Commons Attribution-Share Alike 4.0 (CC BY-SA) license: https://creativecommons.org/licenses/by-sa/4.0
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from pandas.plotting import parallel_coordinates
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn import metrics
# load through url
url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
attributes = ["sepal_length", "sepal_width", "petal_length", "petal_width", "species"]
data = pd.read_csv(url, names = attributes)
data.columns = attributes
data.head()
| sepal_length | sepal_width | petal_length | petal_width | species | |
|---|---|---|---|---|---|
| 0 | 5.1 | 3.5 | 1.4 | 0.2 | Iris-setosa |
| 1 | 4.9 | 3.0 | 1.4 | 0.2 | Iris-setosa |
| 2 | 4.7 | 3.2 | 1.3 | 0.2 | Iris-setosa |
| 3 | 4.6 | 3.1 | 1.5 | 0.2 | Iris-setosa |
| 4 | 5.0 | 3.6 | 1.4 | 0.2 | Iris-setosa |
# types for the columns
data.dtypes
sepal_length float64 sepal_width float64 petal_length float64 petal_width float64 species object dtype: object
# number of instances in each class
data.groupby('species').size()
species Iris-setosa 50 Iris-versicolor 50 Iris-virginica 50 dtype: int64
# Take out a test set
train, test = train_test_split(data, test_size = 0.4, stratify = data['species'], random_state = 42)
# number of instances in each class in training data
train.groupby('species').size()
species Iris-setosa 30 Iris-versicolor 30 Iris-virginica 30 dtype: int64
# histograms
n_bins = 10
fig, axs = plt.subplots(2, 2)
axs[0,0].hist(train['sepal_length'], bins = n_bins);
axs[0,0].set_title('Sepal Length');
axs[0,1].hist(train['sepal_width'], bins = n_bins);
axs[0,1].set_title('Sepal Width');
axs[1,0].hist(train['petal_length'], bins = n_bins);
axs[1,0].set_title('Petal Length');
axs[1,1].hist(train['petal_width'], bins = n_bins);
axs[1,1].set_title('Petal Width');
# add some spacing between subplots
fig.tight_layout(pad=1.0);
# Model development
X_train = train[['sepal_length','sepal_width','petal_length','petal_width']]
y_train = train.species
X_test = test[['sepal_length','sepal_width','petal_length','petal_width']]
y_test = test.species
# decision tree
mod_dt = DecisionTreeClassifier(max_depth = 3, random_state = 1)
mod_dt.fit(X_train,y_train)
prediction=mod_dt.predict(X_test)
print('The accuracy of the Decision Tree is',"{:.3f}".format(metrics.accuracy_score(prediction,y_test)))
The accuracy of the Decision Tree is 0.983
mod_dt.feature_importances_
array([0. , 0. , 0.42430866, 0.57569134])
# set figure size
fn = ["sepal_length", "sepal_width", "petal_length", "petal_width"]
cn = ['setosa', 'versicolor', 'virginica']
plt.figure(figsize = (10,8))
plot_tree(mod_dt, feature_names = fn, class_names = cn, filled = True);
