25/04/2024, 21:35 logistics_regression+softmax_regression.

ipynb - Colab

Logistics regression using IRIS dataset

import numpy as np
import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_score, recall_score, confusion_matrix

# Load the Iris dataset

iris = load_iris()

# Split the data into training and testing sets

X = iris["data"][:, 3:] # petal width
y = (iris["target"] == 2).astype(np.int64) # 1 if Iris virginica, else 0
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
print(y_train)

[0 1 1 1 1 0 1 0 0 1 1 1 1 0 1 0 0 1 0 0 0 0 1 0 0 1 0 0 0 0 0 1 0 0 0 1 0
0 1 1 1 1 0 0 1 1 0 1 0 1 1 0 0 1 0 0 0 0 1 1 0 0 0 0 0 0 0 0 0 1 0 1 0 0
1 0 1 0 0 1 0 1 0 0 0 1 1 0 0 0 0 1 1 0 0 0 0 0 0 0 0 1 0 1 0]

# Create a logistic regression model

model = LogisticRegression()

# Train the model

model.fit(X_train, y_train)

▾ LogisticRegression
LogisticRegression()

# Make predictions on the test set

y_pred = model.predict(X_test)

print(y_pred)

[1 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 1 0 0 0 0 0 1 0 0 1 1 0 0
0 0 0 1 0 1 0 0]

# Calculate the accuracy, precision, recall, and confusion matrix

accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
confusion_matrix = confusion_matrix(y_test, y_pred)

# Print the results

print("Accuracy:", accuracy)
print("Precision:", precision)
print("Recall:", recall)
print("Confusion matrix:\n", confusion_matrix)

Accuracy: 0.9777777777777777
Precision: 1.0
Recall: 0.9090909090909091
Confusion matrix:
[[34 0]
[ 1 10]]

Softmax Regression on IRIS dataset

import numpy as np
from sklearn.datasets import load_iris
from sklearn.linear_model import LogisticRegression

# Load the iris dataset

iris = load_iris()

print(iris)

{'data': array([[5.1, 3.5, 1.4, 0.2],

[4.9, 3. , 1.4, 0.2],
[4.7, 3.2, 1.3, 0.2],
[4.6, 3.1, 1.5, 0.2],

https://colab.research.google.com/drive/1FGTXQRqv54bMh6Jz3SOwV17Ld3nchbTG#scrollTo=Fbt4Bblu_7ss&printMode=true 1/3
25/04/2024, 21:35 logistics_regression+softmax_regression.ipynb - Colab
[5. , 3.6, 1.4, 0.2],
[5.4, 3.9, 1.7, 0.4],
[4.6, 3.4, 1.4, 0.3],
[5. , 3.4, 1.5, 0.2],
[4.4, 2.9, 1.4, 0.2],
[4.9, 3.1, 1.5, 0.1],
[5.4, 3.7, 1.5, 0.2],
[4.8, 3.4, 1.6, 0.2],
[4.8, 3. , 1.4, 0.1],
[4.3, 3. , 1.1, 0.1],
[5.8, 4. , 1.2, 0.2],
[5.7, 4.4, 1.5, 0.4],
[5.4, 3.9, 1.3, 0.4],
[5.1, 3.5, 1.4, 0.3],
[5.7, 3.8, 1.7, 0.3],
[5.1, 3.8, 1.5, 0.3],
[5.4, 3.4, 1.7, 0.2],
[5.1, 3.7, 1.5, 0.4],
[4.6, 3.6, 1. , 0.2],
[5.1, 3.3, 1.7, 0.5],
[4.8, 3.4, 1.9, 0.2],
[5. , 3. , 1.6, 0.2],
[5. , 3.4, 1.6, 0.4],
[5.2, 3.5, 1.5, 0.2],
[5.2, 3.4, 1.4, 0.2],
[4.7, 3.2, 1.6, 0.2],
[4.8, 3.1, 1.6, 0.2],
[5.4, 3.4, 1.5, 0.4],
[5.2, 4.1, 1.5, 0.1],
[5.5, 4.2, 1.4, 0.2],
[4.9, 3.1, 1.5, 0.2],
[5. , 3.2, 1.2, 0.2],
[5.5, 3.5, 1.3, 0.2],
[4.9, 3.6, 1.4, 0.1],
[4.4, 3. , 1.3, 0.2],
[5.1, 3.4, 1.5, 0.2],
[5. , 3.5, 1.3, 0.3],
[4.5, 2.3, 1.3, 0.3],
[4.4, 3.2, 1.3, 0.2],
[5. , 3.5, 1.6, 0.6],
[5.1, 3.8, 1.9, 0.4],
[4.8, 3. , 1.4, 0.3],
[5.1, 3.8, 1.6, 0.2],
[4.6, 3.2, 1.4, 0.2],
[5.3, 3.7, 1.5, 0.2],
[5. , 3.3, 1.4, 0.2],
[7. , 3.2, 4.7, 1.4],
[6.4, 3.2, 4.5, 1.5],
[6.9, 3.1, 4.9, 1.5],
[5.5, 2.3, 4. , 1.3],
[6.5, 2.8, 4.6, 1.5],
[5.7, 2.8, 4.5, 1.3],
[6 3 3 3 4 7 1 6]

# Split the data into training and testing sets

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.25)

# Create a softmax regression classifier

clf = LogisticRegression(multi_class='multinomial', solver='lbfgs')

# Train the classifier

clf.fit(X_train, y_train)

▾ LogisticRegression
LogisticRegression(multi_class='multinomial')

# Make predictions on the train set

y_pred_train = clf.predict(X_train)

# Make predictions on the test set

y_pred = clf.predict(X_test)

# Calculate the accuracy

accuracy = accuracy_score(y_train, y_pred_train)
print(accuracy)

0.9910714285714286

# Calculate the accuracy

accuracy = accuracy_score(y_test, y_pred)

https://colab.research.google.com/drive/1FGTXQRqv54bMh6Jz3SOwV17Ld3nchbTG#scrollTo=Fbt4Bblu_7ss&printMode=true 2/3
25/04/2024, 21:35 logistics_regression+softmax_regression.ipynb - Colab

# Print the accuracy for test set

print("Accuracy:", accuracy)

Accuracy: 0.9473684210526315

from sklearn.metrics import confusion_matrix

# Compute the confusion matrix
cm = confusion_matrix(y_test, y_pred)

# Print the confusion matrix

print(cm)

[[13 0 0]
[ 0 12 2]
[ 0 0 11]]

from sklearn.metrics import confusion_matrix

# Compute the confusion matrix for train set
cm = confusion_matrix(y_train, y_pred_train)

# Print the confusion matrix for train set

print(cm)

[[37 0 0]
[ 0 35 1]
[ 0 0 39]]

# Create a new iris flower

new_flower = [5.0, 3.6, 1.3, 0.25]

# Predict the species of the new flower

prediction = clf.predict([new_flower])

# Print the prediction

print("Predicted species:", iris.target_names[prediction])

Predicted species: ['setosa']

https://colab.research.google.com/drive/1FGTXQRqv54bMh6Jz3SOwV17Ld3nchbTG#scrollTo=Fbt4Bblu_7ss&printMode=true 3/3