import pandas as pd

from google.colab import files
uploaded = files.upload()

Choose Files No file chosen

import io
Iris = pd.read_csv(io.BytesIO(uploaded['Iris.csv']))
Iris

Id SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Species

0 1 5.1 3.5 1.4 0.2 Iris-setosa

1 2 4.9 3.0 1.4 0.2 Iris-setosa

2 3 4.7 3.2 1.3 0.2 Iris-setosa

3 4 4.6 3.1 1.5 0.2 Iris-setosa

4 5 5.0 3.6 1.4 0.2 Iris-setosa

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

145 146 6.7 3.0 5.2 2.3 Iris-virginica

146 147 6.3 2.5 5.0 1.9 Iris-virginica

147 148 6.5 3.0 5.2 2.0 Iris-virginica

148 149 6.2 3.4 5.4 2.3 Iris-virginica

149 150 5.9 3.0 5.1 1.8 Iris-virginica

150 rows × 6 columns

import pandas as pd
 
# We'll also import seaborn, a Python graphing library
import warnings # current version of seaborn generates a bunch of warnings that we'll igno
warnings.filterwarnings("ignore")
import seaborn as sns
import matplotlib.pyplot as plt
sns.set(style="white", color_codes=True)

Iris.head()
 Id SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Species

0 1 5.1 3.5 1.4 0.2 Iris-setosa

1 2 4.9 3.0 1.4 0.2 Iris-setosa

2 3 4.7 3.2 1.3 0.2 Iris-setosa

Iris-setosa
4 5 50

5.0 3.6 1.4 0.2 Iris-setosa

Iris-virginica 50

Name: Species, dtype: int64

# The first way we can plot things is using the .plot extension from Pandas dataframes
# We'll use this to make a scatterplot of the Iris features.
Iris.plot(kind="scatter", x="SepalLengthCm", y="SepalWidthCm")

*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoide
<matplotlib.axes._subplots.AxesSubplot at 0x7fb55c046750>

# We can also use the seaborn library to make a similar plot
# A seaborn jointplot shows bivariate scatterplots and univariate histograms in the same f
sns.jointplot(x="SepalLengthCm", y="SepalWidthCm", data=Iris, size=10)
 <seaborn.axisgrid.JointGrid at 0x7fb55bf27150>

# One piece of information missing in the plots above is what species each plant is
# We'll use seaborn's FacetGrid to color the scatterplot by species
sns.FacetGrid(Iris, hue="Species", size=5) \
   .map(plt.scatter, "SepalLengthCm", "SepalWidthCm") \
   .add_legend()

<seaborn.axisgrid.FacetGrid at 0x7fb55bd81710>

# We can look at an individual feature in Seaborn through a boxplot
sns.boxplot(x="Species", y="PetalLengthCm", data=Iris)
 <matplotlib.axes._subplots.AxesSubplot at 0x7fb55bc8ced0>

# A final seaborn plot useful for looking at univariate relations is the kdeplot,
# which creates and visualizes a kernel density estimate of the underlying feature
sns.FacetGrid(Iris, hue="Species", size=6) \
   .map(sns.kdeplot, "SepalLengthCm") \
   .add_legend()

<seaborn.axisgrid.FacetGrid at 0x7fb5657b0350>

# Another useful seaborn plot is the pairplot, which shows the bivariate relation
# between each pair of features
# 
# From the pairplot, we'll see that the Iris-setosa species is separataed from the other
# two across all feature combinations
sns.pairplot(Iris.drop("Id", axis=1), hue="Species", size=3)
 <seaborn.axisgrid.PairGrid at 0x7fb56579ae50>

from sklearn.datasets import load_iris
from sklearn import tree
iris = load_iris()
X, y = iris.data, iris.target
clf = tree.DecisionTreeClassifier()
clf = clf.fit(X, y)
clf

DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini',

max_depth=None, max_features=None, max_leaf_nodes=None,

min_impurity_decrease=0.0, min_impurity_split=None,

min_samples_leaf=1, min_samples_split=2,

min_weight_fraction_leaf=0.0, presort='deprecated',

random_state=None, splitter='best')

tree.plot_tree(clf) 

[Text(167.4, 199.32, 'X[2] <= 2.45\ngini = 0.667\nsamples = 150\nvalue = [50, 50, 50]
Text(141.64615384615385, 163.07999999999998, 'gini = 0.0\nsamples = 50\nvalue = [50,
Text(193.15384615384616, 163.07999999999998, 'X[3] <= 1.75\ngini = 0.5\nsamples = 10
Text(103.01538461538462, 126.83999999999999, 'X[2] <= 4.95\ngini = 0.168\nsamples =
Text(51.50769230769231, 90.6, 'X[3] <= 1.65\ngini = 0.041\nsamples = 48\nvalue = [0,
Text(25.753846153846155, 54.359999999999985, 'gini = 0.0\nsamples = 47\nvalue = [0,
Text(77.26153846153846, 54.359999999999985, 'gini = 0.0\nsamples = 1\nvalue = [0, 0,
Text(154.52307692307693, 90.6, 'X[3] <= 1.55\ngini = 0.444\nsamples = 6\nvalue = [0,
Text(128.76923076923077, 54.359999999999985, 'gini = 0.0\nsamples = 3\nvalue = [0, 0
Text(180.27692307692308, 54.359999999999985, 'X[0] <= 6.95\ngini = 0.444\nsamples =
Text(154.52307692307693, 18.119999999999976, 'gini = 0.0\nsamples = 2\nvalue = [0, 2
Text(206.03076923076924, 18.119999999999976, 'gini = 0.0\nsamples = 1\nvalue = [0, 0
Text(283.2923076923077, 126.83999999999999, 'X[2] <= 4.85\ngini = 0.043\nsamples = 4
Text(257.53846153846155, 90.6, 'X[1] <= 3.1\ngini = 0.444\nsamples = 3\nvalue = [0,
Text(231.7846153846154, 54.359999999999985, 'gini = 0.0\nsamples = 2\nvalue = [0, 0,
Text(283.2923076923077, 54.359999999999985, 'gini = 0.0\nsamples = 1\nvalue = [0, 1,
Text(309.04615384615386, 90.6, 'gini = 0.0\nsamples = 43\nvalue = [0, 0, 43]')]

import graphviz 

dot_data = tree.export_graphviz(clf, out_file=None) 

graph = graphviz.Source(dot_data)

graph.render("iris") 

'iris.pdf'

dot_data = tree.export_graphviz(clf, out_file=None, 
feature names=iris feature names
...                      feature_names=iris.feature_names,  
...                      class_names=iris.target_names,  
...                      filled=True, rounded=True,  
...                      special_characters=True)  

graph = graphviz.Source(dot_data)

graph 
 petal length (c
gini = 0
samples
value = [50
class = s

True

gini = 0.0
samples = 50
value = [50, 0, 0]
class = setosa

petal length (cm) ≤ 4