Duplicate from DHEIVER/timeseries-anomaly-detection-autoencoders

Co-authored-by: Dheiver Santos <DHEIVER@users.noreply.huggingface.co>

.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: DHEIVER/timeseries-anomaly-detection-autoencoders
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,85 @@
+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(figsize=(12, 6))
+    df_test_value.plot(legend=False, ax=ax)
+    ax.set_xlabel("Time")
+    ax.set_ylabel("Value")
+    ax.set_title("Input Test Data")
+    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(figsize=(12, 6))
+    data.plot(legend=False, ax=ax)
+    df_subset.plot(legend=False, ax=ax, color="r")
+    ax.set_xlabel("Time")
+    ax.set_ylabel("Value")
+    ax.set_title("Anomalous Data Points")
+    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.outputs.Image()
+
+iface = gr.Interface(
+    fn=master,
+    inputs=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."
+)
+
+iface.launch()

example_1.csv

@@ -0,0 +1,44 @@
+timestamp,value
+2023-07-01 09:00:00,0.256
+2023-07-01 09:01:00,0.342
+2023-07-01 09:02:00,0.421
+2023-07-01 09:03:00,0.189
+2023-07-01 09:04:00,0.289
+2023-07-01 09:05:00,0.512
+2023-07-01 09:06:00,0.367
+2023-07-01 09:07:00,0.428
+2023-07-01 09:08:00,0.196
+2023-07-01 09:09:00,0.317
+2023-07-01 09:10:00,0.425
+2023-07-01 09:11:00,0.274
+2023-07-01 09:12:00,0.312
+2023-07-01 09:13:00,0.397
+2023-07-01 09:14:00,0.251
+2023-07-01 09:15:00,0.361
+2023-07-01 09:16:00,0.429
+2023-07-01 09:17:00,0.185
+2023-07-01 09:18:00,0.327
+2023-07-01 09:19:00,0.412
+2023-07-01 09:20:00,0.197
+2023-07-01 09:21:00,0.303
+2023-07-01 09:22:00,0.439
+2023-07-01 09:23:00,0.254
+2023-07-01 09:24:00,0.367
+2023-07-01 09:25:00,0.421
+2023-07-01 09:26:00,0.193
+2023-07-01 09:27:00,0.297
+2023-07-01 09:28:00,0.416
+2023-07-01 09:29:00,0.224
+2023-07-01 09:30:00,0.359
+2023-07-01 09:31:00,0.428
+2023-07-01 09:32:00,0.165
+2023-07-01 09:33:00,0.338
+2023-07-01 09:34:00,0.405
+2023-07-01 09:35:00,0.217
+2023-07-01 09:36:00,0.292
+2023-07-01 09:37:00,0.434
+2023-07-01 09:38:00,0.235
+2023-07-01 09:39:00,0.341
+2023-07-01 09:40:00,0.398
+2023-07-01 09:41:00,0.203
+2023-07-01 09:42:00,0.282

example_2.csv

@@ -0,0 +1,43 @@
+timestamp,value
+2023-07-01 08:00:00,10.2
+2023-07-01 08:01:00,10.5
+2023-07-01 08:02:00,11.1
+2023-07-01 08:03:00,9.8
+2023-07-01 08:04:00,11.5
+2023-07-01 08:05:00,10.9
+2023-07-01 08:06:00,10.7
+2023-07-01 08:07:00,11.2
+2023-07-01 08:08:00,10.4
+2023-07-01 08:09:00,10.6
+2023-07-01 08:10:00,11.3
+2023-07-01 08:11:00,10.8
+2023-07-01 08:12:00,10.5
+2023-07-01 08:13:00,10.2
+2023-07-01 08:14:00,11.1
+2023-07-01 08:15:00,10.3
+2023-07-01 08:16:00,10.6
+2023-07-01 08:17:00,11.0
+2023-07-01 08:18:00,10.8
+2023-07-01 08:19:00,10.4
+2023-07-01 08:20:00,11.2
+2023-07-01 08:21:00,10.7
+2023-07-01 08:22:00,10.5
+2023-07-01 08:23:00,10.9
+2023-07-01 08:24:00,10.2
+2023-07-01 08:25:00,10.8
+2023-07-01 08:26:00,11.3
+2023-07-01 08:27:00,10.6
+2023-07-01 08:28:00,10.3
+2023-07-01 08:29:00,11.1
+2023-07-01 08:30:00,10.7
+2023-07-01 08:31:00,10.9
+2023-07-01 08:32:00,11.2
+2023-07-01 08:33:00,10.4
+2023-07-01 08:34:00,10.2
+2023-07-01 08:35:00,10.6
+2023-07-01 08:36:00,11.0
+2023-07-01 08:37:00,10.5
+2023-07-01 08:38:00,10.8
+2023-07-01 08:39:00,11.1
+2023-07-01 08:40:00,10.3
+2023-07-01 08:41:00,10.7

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+pandas
+numpy
+matplotlib
+tensorflow

scaler.json

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