Scribd
Upload
2 views3 pages

Code 12 Updated

The document outlines a data analysis process using Python, focusing on fault classification from multiple datasets. It includes data loading, visualization of fault distribution, feature correlation heatmap, PCA for dimensionality reduction, and training of Random Forest and SVM models. Finally, it evaluates model performance using confusion matrices and classification reports.

Uploaded by

20112042paren
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
2 views3 pages

Code 12 Updated

The document outlines a data analysis process using Python, focusing on fault classification from multiple datasets. It includes data loading, visualization of fault distribution, feature correlation heatmap, PCA for dimensionality reduction, and training of Random Forest and SVM models. Finally, it evaluates model performance using confusion matrices and classification reports.

Uploaded by

20112042paren
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 3

import pandas as pd

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.decomposition import PCA
from sklearn.model_selection import train_test_split, cross_val_score, ShuffleSplit
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
from mpl_toolkits.mplot3d import Axes3D

# Set plot styles


plt.rcParams.update({'font.size': 14, "font.family": "Times New Roman"})

# ----------------------
# Load Datasets
# ----------------------
# Read each CSV file separately
df_f0l = pd.read_csv(r'/F0L.csv')
df_f1l = pd.read_csv(r'/F1L.csv')
df_f5l = pd.read_csv(r'/F5L.csv')

# Concatenate the DataFrames into a single DataFrame


df1 = pd.concat([df_f0l, df_f1l, df_f5l], ignore_index=True)

# **Add a 'Fault_Type' column to df1 based on the source file**


df1['Fault_Type'] = pd.Series(['F0'] * len(df_f0l) + ['F1'] * len(df_f1l) + ['F5']
* len(df_f5l))

# Read each CSV file separately for df2


df_f0m = pd.read_csv(r'/F0M.csv')
df_f1m = pd.read_csv(r'/F1M.csv')
df_f5m = pd.read_csv(r'/F5M.csv')

# Concatenate the DataFrames into a single DataFrame


df2 = pd.concat([df_f0m, df_f1m, df_f5m], ignore_index=True)

# **Add a 'Fault_Type' column to df2 based on the source file**


df2['Fault_Type'] = pd.Series(['F0'] * len(df_f0m) + ['F1'] * len(df_f1m) + ['F5']
* len(df_f5m))

# ----------------------
# Data Visualization: Fault Distribution
# ----------------------
plt.figure(figsize=(5, 5))
# Assuming 'Fault_Type' is the correct column representing fault types
plt.pie(df1['Fault_Type'].value_counts(), labels=df1['Fault_Type'].unique(),
autopct='%2.1f%%', colors=sns.color_palette("pastel"))
plt.title("Fault Distribution in Limited Power Dataset")
plt.show()

# ----------------------
# Feature Correlation Heatmap
# ----------------------
X = df1.iloc[:, 1:-1] # Features
# Assuming 'Fault_Type' is the target variable column
Y = df1['Fault_Type'] # Target Labels

plt.figure(figsize=(12, 10))
sns.heatmap(X.corr(), annot=True, cmap='coolwarm', fmt=".2f")
plt.title("Feature Correlation Heatmap")
plt.show()
# ----------------------
# Data Preprocessing
# ----------------------
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2,
shuffle=True, random_state=42)
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# ----------------------
# PCA: Dimensionality Reduction
# ----------------------
for i in range(1, 14):
pca = PCA(n_components=i)
pca.fit(X_train_scaled)
print(f"Cumulative explained variance for {i} components:
{np.sum(pca.explained_variance_ratio_):.4f}")

# Apply PCA with 2 components


pca_2 = PCA(n_components=2)
X_pca_2D = pca_2.fit_transform(X_train_scaled)
principalDf = pd.DataFrame(data=X_pca_2D, columns=['PC1', 'PC2'])
principalDf['Fault'] = np.array(y_train)

plt.figure(figsize=(10, 8))
sns.scatterplot(x=principalDf['PC1'], y=principalDf['PC2'],
hue=principalDf['Fault'], palette='Dark2', alpha=0.7)
plt.title("2D PCA Visualization")
plt.xlabel("Principal Component 1")
plt.ylabel("Principal Component 2")
plt.show()

# 3D PCA Visualization
pca_3 = PCA(n_components=3)
X_pca_3D = pca_3.fit_transform(X_train_scaled)
principalDf = pd.DataFrame(data=X_pca_3D, columns=['PC1', 'PC2', 'PC3'])
principalDf['Fault'] = np.array(y_train)

fig = plt.figure(figsize=(10, 10))


ax = fig.add_subplot(111, projection='3d')
colors = sns.color_palette("husl", len(y_train.unique()))
for fault, color in zip(y_train.unique(), colors):
indices = principalDf['Fault'] == fault
ax.scatter(principalDf.loc[indices, 'PC1'],
principalDf.loc[indices, 'PC2'],
principalDf.loc[indices, 'PC3'],
c=[color], label=fault, s=50)
ax.set_xlabel('Principal Component 1')
ax.set_ylabel('Principal Component 2')
ax.set_zlabel('Principal Component 3')
ax.set_title('3D PCA Visualization')
ax.legend()
plt.show()

# ----------------------
# Train & Evaluate Models
# ----------------------
rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
rf_model.fit(X_train_scaled, y_train)
y_pred_rf = rf_model.predict(X_test_scaled)

svm_model = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=42)


svm_model.fit(X_train_scaled, y_train)
y_pred_svm = svm_model.predict(X_test_scaled)

# ----------------------
# Confusion Matrix Plot
# ----------------------
def plot_confusion_matrix(y_true, y_pred, model_name):
cm = confusion_matrix(y_true, y_pred)
plt.figure(figsize=(8, 6))
sns.heatmap(cm, annot=True, fmt="d", cmap="viridis",
xticklabels=np.unique(y_true), yticklabels=np.unique(y_true))
plt.xlabel("Predicted Label")
plt.ylabel("True Label")
plt.title(f"Confusion Matrix - {model_name}")
plt.show()

plot_confusion_matrix(y_test, y_pred_rf, "Random Forest")


plot_confusion_matrix(y_test, y_pred_svm, "SVM")

# ----------------------
# Final Model Evaluations
# ----------------------
print("\nRandom Forest Results:")
print(f"Accuracy: {accuracy_score(y_test, y_pred_rf):.4f}")
print(classification_report(y_test, y_pred_rf))

print("\nSVM Results:")
print(f"Accuracy: {accuracy_score(y_test, y_pred_svm):.4f}")
print(classification_report(y_test, y_pred_svm))

You might also like