Comparison of Classifiers
Uploaded by
pnagakalyan.aimlComparison of Classifiers
Uploaded by
pnagakalyan.aimlComparison_of_Classifiers
November 5, 2024
[1]: #Performance analysis of Classification Algorithms on a IRIS dataset
[2]: import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report,␣
↪confusion_matrix
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import cross_val_score
[3]: # The Iris dataset is a classic dataset in the field of machine learning and␣
↪statistics, widely used for classification tasks. :
# Features of the Iris Dataset
# The dataset consists of four features measured for each flower sample:
# 1. Sepal Length: The length of the sepal in centimeters.
# 2. Sepal Width: The width of the sepal in centimeters.
# 3. Petal Length: The length of the petal in centimeters.
# 4. Petal Width: The width of the petal in centimeters.
# Species of Iris Flowers
# The dataset includes three species of the Iris flower:
# 1. Iris Setosa:Typically has shorter and narrower petals and sepals.
# 2.Iris Versicolor:Intermediate flower size compared to Setosa and Virginica.
# 3. Iris Virginica: Usually has the largest petals and sepals among the three␣
↪species.
# - Total Samples: 150
# - Samples per Species: 50 for each species
# - Total Features: 4 (Sepal Length, Sepal Width, Petal Length, Petal Width)
# - Target Variable: Species of the Iris flower (Setosa, Versicolor, Virginica)
1
[4]: # Load the Iris dataset
data = load_iris()
X = data.data # Features
y = data.target # Target labels
[5]: # Dictionary to store accuracy results for final comparison
accuracy_results = {}
[6]: # 1. Decision Tree Classifier
decision_tree = DecisionTreeClassifier()
# Perform 5-fold cross-validation
dt_scores = cross_val_score(decision_tree, X, y, cv=5)
dt_accuracy = dt_scores.mean()
accuracy_results["Decision Tree"] = dt_accuracy
# Train the model on the full dataset
decision_tree.fit(X, y)
dt_y_pred = decision_tree.predict(X)
# Print results
print("\nDecision Tree Results:")
print(f"Cross-Validation Accuracy: {dt_accuracy:.2f}")
print("Classification Report:\n", classification_report(y, dt_y_pred,␣
↪target_names=data.target_names, zero_division=1))
# Confusion matrix and plot
dt_conf_matrix = confusion_matrix(y, dt_y_pred)
plt.figure(figsize=(6, 4))
sns.heatmap(dt_conf_matrix, annot=True, fmt="d", cmap="Blues",
xticklabels=data.target_names, yticklabels=data.target_names)
plt.title("Decision Tree - Confusion Matrix")
plt.xlabel("Predicted")
plt.ylabel("Actual")
plt.show()
Decision Tree Results:
Cross-Validation Accuracy: 0.96
Classification Report:
precision recall f1-score support
setosa 1.00 1.00 1.00 50
versicolor 1.00 1.00 1.00 50
virginica 1.00 1.00 1.00 50
accuracy 1.00 150
macro avg 1.00 1.00 1.00 150
2
weighted avg 1.00 1.00 1.00 150
[7]: # 2. K-Nearest Neighbors Classifier
knn = KNeighborsClassifier(n_neighbors=3)
# Perform 5-fold cross-validation
knn_scores = cross_val_score(knn, X, y, cv=5)
knn_accuracy = knn_scores.mean()
accuracy_results["K-Nearest Neighbors"] = knn_accuracy
# Train the model on the full dataset
knn.fit(X, y)
knn_y_pred = knn.predict(X)
# Print results
print("\nK-Nearest Neighbors Results:")
print(f"Cross-Validation Accuracy: {knn_accuracy:.2f}")
print("Classification Report:\n", classification_report(y, knn_y_pred,␣
↪target_names=data.target_names, zero_division=1))
# Confusion matrix and plot
knn_conf_matrix = confusion_matrix(y, knn_y_pred)
3
plt.figure(figsize=(6, 4))
sns.heatmap(knn_conf_matrix, annot=True, fmt="d", cmap="Blues",
xticklabels=data.target_names, yticklabels=data.target_names)
plt.title("K-Nearest Neighbors - Confusion Matrix")
plt.xlabel("Predicted")
plt.ylabel("Actual")
plt.show()
K-Nearest Neighbors Results:
Cross-Validation Accuracy: 0.97
Classification Report:
precision recall f1-score support
setosa 1.00 1.00 1.00 50
versicolor 0.94 0.94 0.94 50
virginica 0.94 0.94 0.94 50
accuracy 0.96 150
macro avg 0.96 0.96 0.96 150
weighted avg 0.96 0.96 0.96 150
4
[8]: # 3. Logistic Regression Classifier
logistic_regression = LogisticRegression(max_iter=200)
# Perform 5-fold cross-validation
lr_scores = cross_val_score(logistic_regression, X, y, cv=5)
lr_accuracy = lr_scores.mean()
accuracy_results["Logistic Regression"] = lr_accuracy
# Train the model on the full dataset
logistic_regression.fit(X, y)
lr_y_pred = logistic_regression.predict(X)
# Print results
print("\nLogistic Regression Results:")
print(f"Cross-Validation Accuracy: {lr_accuracy:.2f}")
print("Classification Report:\n", classification_report(y, lr_y_pred,␣
↪target_names=data.target_names, zero_division=1))
# Confusion matrix and plot
lr_conf_matrix = confusion_matrix(y, lr_y_pred)
plt.figure(figsize=(6, 4))
sns.heatmap(lr_conf_matrix, annot=True, fmt="d", cmap="Blues",
xticklabels=data.target_names, yticklabels=data.target_names)
plt.title("Logistic Regression - Confusion Matrix")
plt.xlabel("Predicted")
plt.ylabel("Actual")
plt.show()
Logistic Regression Results:
Cross-Validation Accuracy: 0.97
Classification Report:
precision recall f1-score support
setosa 1.00 1.00 1.00 50
versicolor 0.98 0.94 0.96 50
virginica 0.94 0.98 0.96 50
accuracy 0.97 150
macro avg 0.97 0.97 0.97 150
weighted avg 0.97 0.97 0.97 150
5
[9]: # Print a summary of cross-validation accuracies for all classifiers
print("\nFinal Comparison of Cross-Validation Accuracies:")
for name, accuracy in accuracy_results.items():
print(f"{name}: {accuracy:.2f}")
Final Comparison of Cross-Validation Accuracies:
Decision Tree: 0.96
K-Nearest Neighbors: 0.97
Logistic Regression: 0.97