-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathiris_flower_classification.py
242 lines (160 loc) · 113 KB
/
iris_flower_classification.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
# -*- coding: utf-8 -*-
"""IRIS FLOWER - CLASSIFICATION.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1I_ZA4FHu8nU6cibAU6D4zVNEl5UdNXfs
# **IRIS FLOWER CLASSIFICATION**
**Download Dataset here** [IRIS FLOWER CLASSIFICATION](https://drive.google.com/file/d/1TWJNm-fUQYjaPGS9Y9tD9DdQ4GR3SjtR/view?usp=share_link)
"""
from google.colab import drive
drive.mount('/content/drive')
"""### Knowing about the Dataset
**Importing the Required Libraries**
"""
# Pandas Library for Dataframe
import pandas as pd
# Numpy Library for Numerical Calculations
import numpy as np
# Matplotlib and Seaborn for Plottings
import matplotlib.pyplot as plt
import seaborn as sns
# Pickle Library for Saving the Model
import pickle
# Train_Test_Split for splitting the Dataset
from sklearn.model_selection import train_test_split
# KFold and Cross_Val_Score for Validation
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
# Logistic Regression, Decision Tree, K Neighbors, Naive Bayes, SVC and Linear Discriminant are Models
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
# Accuracy Score, Classification Report and Confusion Matrix is for Analysis of Models
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
"""**Reading informations in the Dataset**"""
iris = pd.read_csv("/content/drive/MyDrive/Oasis Infobyte/Data Science - Internship/Iris-Flower-Classification/Iris.csv")
"""**Checking for null values in Data**"""
iris.isnull().sum()
"""**Checking the First Five Values in the Data**"""
iris.head()
"""**Checking the Last Five Values in the Data**"""
iris.tail()
"""**Dropping the unused Column in the Dataset**
In ML, we will not be using the unique identifiers so we are reoving that column
"""
iris = iris.drop(['Id'], axis=1)
iris.columns
"""**Dimensions of the Dataset**"""
iris.shape
"""**Describing the Dataset**"""
print(iris.describe())
"""**Checking for the classes in the Data**"""
print(iris.groupby('Species').size())
"""### Visualization of the Data
**Classes distribution over Count of each class Plotting**
"""
species_plot = iris['Species'].value_counts().plot.bar(title = 'Flower Class Distribution')
species_plot.set_xlabel('Class',size=20)
species_plot.set_ylabel('Count',size=20)
"""Each class has equal distribution
**Box and Whisker Plot**
"""
iris.plot(kind = 'box', subplots = True, layout = (2, 2),
sharex = False, sharey = False, title = "Box and Whisker plot for each Attribute")
plt.show()
"""To check the Attribute Distribution
**Histogram Plotting**
"""
iris.hist()
plt.show()
"""To check Value Distribution in the Dataset
**Multivariate Scatter Plot**
"""
sns.set(style = "ticks")
sns.pairplot(iris, hue = "Species")
"""Pair-wise Relationship in Dataset
### Data Modeling
**Splitting the Dataset into Training and Testing**
"""
X = iris.drop(['Species'], axis=1)
Y = iris['Species']
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=25)
"""**Checking the Dimensions of Training and Testing Data**"""
print("X_Train Shape:", X_train.shape)
print("X_Test Shape:", X_test.shape)
print("Y_Train Shape:", X_train.shape)
print("Y_Test Shape:", Y_test.shape)
"""### Model Building
**Creating the Models**
"""
# All the Models will be stored in this models list.
models = []
# Linear Models
models.append(('LR', LogisticRegression(solver = 'liblinear', multi_class = "auto")))
models.append(('LDA', LinearDiscriminantAnalysis()))
# Non-linear Models
models.append(('CART', DecisionTreeClassifier()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('GNB', GaussianNB()))
models.append(('SVC', SVC(gamma = "auto")))
print("Model Accuracy")
# Evaluating each Models
names = []
accuracy = []
for name, model in models:
# 15 Cross Fold Validation for each Models
kfold = KFold(n_splits=15)
cv_results = cross_val_score(model, X_train, Y_train, cv=kfold, scoring='accuracy')
# Displaying the Accuracy of each Model in Validation
names.append(name)
accuracy.append(cv_results)
msg = "%s: Accuracy = %f" % (name, cv_results.mean())
print(msg)
"""### Testing Model
**Testing Models**
"""
models = []
# Linear Models
models.append(('LR', LogisticRegression(solver = 'liblinear', multi_class = "auto")))
models.append(('LDA', LinearDiscriminantAnalysis()))
# Non-linear Models
models.append(('CART', DecisionTreeClassifier()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('GNB', GaussianNB()))
models.append(('SVC', SVC(gamma = "auto")))
"""**Creating Function for Testing the Models**"""
def test_model(model):
# Training the Dataset with Training Set
model.fit(X_train, Y_train)
# Predicting the Values with Testing Set
predictions = model.predict(X_test)
# Model Testing Results
print("Accuracy:", accuracy_score(Y_test, predictions))
print("Confusion Matrix:")
print(confusion_matrix(Y_test, predictions))
print("Classification Report:")
print(classification_report(Y_test, predictions))
"""**Testing the Models**"""
# Predicting the Values
for name, model in models:
print("----------------")
print("Testing:", name)
test_model(model)
"""In Testing Top 3 Models are,
1. SVC
2. CART
3. LDA
### Saving Models
**Saving the Best Performed Models**
"""
for name, model in models:
filename = name + ".pkl"
pickle.dump(model, open(filename, 'wb'))
print("Saved all Models")