| import streamlit as st |
| import pandas as pd |
| import numpy as np |
| from sklearn.ensemble import IsolationForest |
| from sklearn.preprocessing import StandardScaler |
| import matplotlib.pyplot as plt |
| from io import BytesIO |
|
|
| |
| st.title("Saif Check Anomalies") |
| st.write("Upload an Excel file to detect anomalies") |
|
|
| uploaded_file = st.file_uploader("Choose an Excel file", type=["xlsx","xls"]) |
|
|
| if uploaded_file: |
| |
| df = pd.read_excel(uploaded_file) |
|
|
| |
| df = df.select_dtypes(include=[int, float]) |
|
|
| |
| scaler = StandardScaler() |
| scaled_data = scaler.fit_transform(df) |
|
|
| |
| clf = IsolationForest(contamination=0.15, random_state=42) |
| clf.fit(scaled_data) |
| predictions = clf.predict(scaled_data) |
|
|
| |
| anomaly_indices = np.where(predictions == -1)[0] |
| anomalies = df.iloc[anomaly_indices] |
|
|
| |
| num_anomalies = len(anomalies) |
| st.subheader(f"Number of anomalies detected: {num_anomalies}") |
|
|
| |
| st.subheader("Anomalies Detected") |
| st.write(anomalies) |
|
|
| |
| for col in df.columns: |
| fig, ax = plt.subplots() |
| ax.plot(df.index, df[col], label="Data") |
| ax.scatter(anomaly_indices, df[col].iloc[anomaly_indices], color='red', label="Anomalies") |
| ax.set_title(f"Anomalies in {col}") |
| ax.legend() |
| st.pyplot(fig) |
