import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
from sklearn.decomposition import PCA
from sklearn.model_selection import train_test_split
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 Multiple CSV Files
# ----------------------
column_names = ['Time', 'Ipv', 'Vpv', 'Vdc', 'ia', 'ib', 'ic', 'va', 'vb', 'vc',
'Iabc', 'If', 'Vabc', 'Vf', 'Fault_Type', 'Power_Condition']
solar_data = pd.DataFrame(columns=column_names)
fault_types = ['F0', 'F1', 'F5']
power_conditions = ['LPP', 'MPP']
for fault in fault_types:
for power in power_conditions:
file_path = '/F0L.csv, /F0M.csv, /F1L.csv, /F1M.csv /F5L.csv, /F5M.csv'
df = pd.read_csv(file_path)
df['Fault_Type'] = fault
df['Power_Condition'] = power
solar_data = pd.concat([solar_data, df], ignore_index=True)
# Encode categorical labels
label_encoder = LabelEncoder()
solar_data['Fault_Type'] = label_encoder.fit_transform(solar_data['Fault_Type'])
solar_data['Power_Condition'] =
label_encoder.fit_transform(solar_data['Power_Condition'])
# Drop unnecessary columns
if 'Time' in solar_data.columns:
solar_data.drop(columns=['Time'], inplace=True)
# Define features and target
X = solar_data.drop(columns=['Fault_Type'])
y = solar_data['Fault_Type']
# Train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,
random_state=42)
# Feature scaling
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)
# ----------------------
# Train & Evaluate Models
# ----------------------
rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
rf_model.fit(X_train, y_train)
y_pred_rf = rf_model.predict(X_test)
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)
# ----------------------
# Model Evaluation
# ----------------------
def evaluate_model(y_true, y_pred, model_name):
print(f"\n{model_name} Results:")
print(f"Accuracy: {accuracy_score(y_true, y_pred):.4f}")
print(classification_report(y_true, y_pred))
print("Confusion Matrix:\n", confusion_matrix(y_true, y_pred))
evaluate_model(y_test, y_pred_rf, "Random Forest")
evaluate_model(y_test, y_pred_svm, "SVM")
# ----------------------
# Feature Importance (Random Forest)
# ----------------------
plt.figure(figsize=(10, 6))
feature_importance = pd.Series(rf_model.feature_importances_,
index=X.columns).sort_values(ascending=False)
sns.barplot(x=feature_importance, y=feature_importance.index, palette='viridis')
plt.xlabel("Feature Importance Score")
plt.ylabel("Features")
plt.title("Feature Importance from Random Forest")
plt.show()
# ----------------------
# 3D Visualization
# ----------------------
feature_x, feature_y, feature_z = 'Vpv', 'Ipv', 'Vdc'
fig = plt.figure(figsize=(10, 7))
ax = fig.add_subplot(111, projection="3d")
scatter = ax.scatter(solar_data[feature_x], solar_data[feature_y],
solar_data[feature_z],
c=solar_data["Fault_Type"], cmap="coolwarm", edgecolors="k")
ax.set_xlabel(feature_x)
ax.set_ylabel(feature_y)
ax.set_zlabel(feature_z)
ax.set_title("3D Visualization of Fault Types")
legend = ax.legend(*scatter.legend_elements(), title="Fault Type")
ax.add_artist(legend)
plt.show()
# Interactive 3D Plot using Plotly
fig = px.scatter_3d(solar_data, x=feature_x, y=feature_y, z=feature_z,
color=solar_data["Fault_Type"].astype(str),
title="Interactive 3D Visualization of Fault Types",
labels={"color": "Fault Type"})
fig.show()
s
