Duplicate from keras-io/timeseries-anomaly-detection-autoencoders

Co-authored-by: Reme Ajayi <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Timeseries Anomaly Detection
+emoji: 🌍
+colorFrom: blue
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.0.1
+app_file: app.py
+pinned: false
+duplicated_from: keras-io/timeseries-anomaly-detection-autoencoders
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,80 @@
+import gradio as gr
+from huggingface_hub import from_pretrained_keras
+import pandas as pd
+import numpy as np
+import json
+from matplotlib import pyplot as plt
+
+f = open('scaler.json')
+scaler = json.load(f)
+
+TIME_STEPS = 288
+
+# Generated training sequences for use in the model.
+def create_sequences(values, time_steps=TIME_STEPS):
+    output = []
+    for i in range(len(values) - time_steps + 1):
+        output.append(values[i : (i + time_steps)])
+    return np.stack(output)
+
+
+def normalize_data(data):
+    df_test_value = (data - scaler["mean"]) / scaler["std"]
+    return df_test_value
+
+def plot_test_data(df_test_value):
+    fig, ax = plt.subplots()
+    df_test_value.plot(legend=False, ax=ax)
+    return fig
+
+def get_anomalies(df_test_value):
+    # Create sequences from test values.
+    x_test = create_sequences(df_test_value.values)
+    model = from_pretrained_keras("keras-io/timeseries-anomaly-detection")
+
+    # Get test MAE loss.
+    x_test_pred = model.predict(x_test)
+    test_mae_loss = np.mean(np.abs(x_test_pred - x_test), axis=1)
+    test_mae_loss = test_mae_loss.reshape((-1))
+
+    # Detect all the samples which are anomalies.
+    anomalies = test_mae_loss > scaler["threshold"]
+    return anomalies
+
+def plot_anomalies(df_test_value, data, anomalies):
+    # data i is an anomaly if samples [(i - timesteps + 1) to (i)] are anomalies
+    anomalous_data_indices = []
+    for data_idx in range(TIME_STEPS - 1, len(df_test_value) - TIME_STEPS + 1):
+        if np.all(anomalies[data_idx - TIME_STEPS + 1 : data_idx]):
+            anomalous_data_indices.append(data_idx)
+    df_subset = data.iloc[anomalous_data_indices]
+    fig, ax = plt.subplots()
+    data.plot(legend=False, ax=ax)
+    df_subset.plot(legend=False, ax=ax, color="r")
+    return fig
+                                      
+def master(file):
+    # read file
+    data = pd.read_csv(file, parse_dates=True, index_col="timestamp")
+    df_test_value = normalize_data(data)
+    # plot input test data
+    plot1 = plot_test_data(df_test_value)
+    # predict
+    anomalies = get_anomalies(df_test_value)
+    #plot anomalous data points
+    plot2 = plot_anomalies(df_test_value, data, anomalies)
+    return plot2
+
+outputs = gr.Plot()
+
+
+iface = gr.Interface(master,
+gr.inputs.File(label="csv file"),
+outputs=outputs, 
+examples=["art_daily_jumpsup.csv"], title="Timeseries Anomaly Detection Using an Autoencoder",
+description = "Anomaly detection of timeseries data.",
+                article = "Space by: <a href=\"https://www.linkedin.com/in/olohireme-ajayi/\">Reme Ajayi</a> <br> Keras Example by <a href=\"https://github.com/pavithrasv/\"> Pavithra Vijay</a>")
+
+
+
+iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+pandas
+numpy
+tensorflow

scaler.json

@@ -0,0 +1 @@
+{"mean": 42.43835333580657, "std": 28.07712228126252, "threshold": 0.1001741920131276}