diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_22_0.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_22_0.png
index 371ff0f9ce..f1779e47c9 100644
Binary files a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_22_0.png and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_22_0.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_12.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_12.png
new file mode 100644
index 0000000000..05c3e7061c
Binary files /dev/null and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_12.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_13.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_13.png
new file mode 100644
index 0000000000..e698324ebb
Binary files /dev/null and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_13.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_15.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_15.png
new file mode 100644
index 0000000000..4a1af53602
Binary files /dev/null and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_15.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_16.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_16.png
new file mode 100644
index 0000000000..681dc8cda3
Binary files /dev/null and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_16.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_2.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_2.png
new file mode 100644
index 0000000000..b06acc2683
Binary files /dev/null and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_2.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_5.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_5.png
index b6ed60cd3d..eb86303716 100644
Binary files a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_5.png and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_5.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_6.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_6.png
new file mode 100644
index 0000000000..fc75c215de
Binary files /dev/null and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_6.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_8.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_8.png
new file mode 100644
index 0000000000..e9d5f53ff2
Binary files /dev/null and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_8.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_9.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_9.png
index 87a397e249..c22b95239f 100644
Binary files a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_9.png and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_24_9.png differ
diff --git a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_6_0.png b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_6_0.png
index ebe040d9ff..dbb33cdd4b 100644
Binary files a/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_6_0.png and b/examples/timeseries/img/timeseries_weather_forecasting/timeseries_weather_forecasting_6_0.png differ
diff --git a/examples/timeseries/ipynb/timeseries_traffic_forecasting.ipynb b/examples/timeseries/ipynb/timeseries_traffic_forecasting.ipynb
index dc5b333332..ea740fe141 100644
--- a/examples/timeseries/ipynb/timeseries_traffic_forecasting.ipynb
+++ b/examples/timeseries/ipynb/timeseries_traffic_forecasting.ipynb
@@ -10,7 +10,7 @@
"\n",
"**Author:** [Arash Khodadadi](https://www.linkedin.com/in/arash-khodadadi-08a02490/)
\n",
"**Date created:** 2021/12/28
\n",
- "**Last modified:** 2023/11/22
\n",
+ "**Last modified:** 2026/02/01
\n",
"**Description:** This example demonstrates how to do timeseries forecasting over graphs."
]
},
@@ -132,9 +132,13 @@
"outputs": [],
"source": [
"url = \"https://github.com/VeritasYin/STGCN_IJCAI-18/raw/master/dataset/PeMSD7_Full.zip\"\n",
- "data_dir = keras.utils.get_file(origin=url, extract=True, archive_format=\"zip\")\n",
- "data_dir = data_dir.rstrip(\"PeMSD7_Full.zip\")\n",
+ "# 1. Download and extract normally\n",
+ "zip_path = keras.utils.get_file(origin=url, extract=True, archive_format=\"zip\")\n",
"\n",
+ "# 2. FIX: Use os.path.dirname to safely get the folder where it was extracted\n",
+ "data_dir = os.path.dirname(zip_path)\n",
+ "\n",
+ "# 3. Construct the paths to the inner files safely\n",
"route_distances = pd.read_csv(\n",
" os.path.join(data_dir, \"PeMSD7_W_228.csv\"), header=None\n",
").to_numpy()\n",
@@ -798,7 +802,7 @@
"source": [
"in_feat = 1\n",
"batch_size = 64\n",
- "epochs = 20\n",
+ "epochs = 1\n",
"input_sequence_length = 12\n",
"forecast_horizon = 3\n",
"multi_horizon = False\n",
diff --git a/examples/timeseries/ipynb/timeseries_weather_forecasting.ipynb b/examples/timeseries/ipynb/timeseries_weather_forecasting.ipynb
index 08238ad8a2..51a7eee220 100644
--- a/examples/timeseries/ipynb/timeseries_weather_forecasting.ipynb
+++ b/examples/timeseries/ipynb/timeseries_weather_forecasting.ipynb
@@ -10,7 +10,7 @@
"\n",
"**Authors:** [Prabhanshu Attri](https://prabhanshu.com/github), [Yashika Sharma](https://github.com/yashika51), [Kristi Takach](https://github.com/ktakattack), [Falak Shah](https://github.com/falaktheoptimist)
\n",
"**Date created:** 2020/06/23
\n",
- "**Last modified:** 2023/11/22
\n",
+ "**Last modified:** 2026/02/01
\n",
"**Description:** This notebook demonstrates how to do timeseries forecasting using a LSTM model."
]
},
@@ -31,6 +31,7 @@
},
"outputs": [],
"source": [
+ "import os\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import keras"
@@ -84,13 +85,18 @@
},
"outputs": [],
"source": [
+ "\n",
"from zipfile import ZipFile\n",
"\n",
"uri = \"https://storage.googleapis.com/tensorflow/tf-keras-datasets/jena_climate_2009_2016.csv.zip\"\n",
"zip_path = keras.utils.get_file(origin=uri, fname=\"jena_climate_2009_2016.csv.zip\")\n",
"zip_file = ZipFile(zip_path)\n",
- "zip_file.extractall()\n",
- "csv_path = \"jena_climate_2009_2016.csv\"\n",
+ "\n",
+ "# FIX: Extract to the cache directory, not the current working directory\n",
+ "zip_file.extractall(path=os.path.dirname(zip_path))\n",
+ "\n",
+ "# FIX: Construct the absolute path safely (works on Windows/Linux/Mac)\n",
+ "csv_path = os.path.join(os.path.dirname(zip_path), \"jena_climate_2009_2016.csv\")\n",
"\n",
"df = pd.read_csv(csv_path)"
]
@@ -236,7 +242,7 @@
"future = 72\n",
"learning_rate = 0.001\n",
"batch_size = 256\n",
- "epochs = 10\n",
+ "epochs = 1\n",
"\n",
"\n",
"def normalize(data, train_split):\n",
diff --git a/examples/timeseries/md/timeseries_weather_forecasting.md b/examples/timeseries/md/timeseries_weather_forecasting.md
index ac5a5bead0..769becdfbf 100644
--- a/examples/timeseries/md/timeseries_weather_forecasting.md
+++ b/examples/timeseries/md/timeseries_weather_forecasting.md
@@ -2,7 +2,7 @@
**Authors:** [Prabhanshu Attri](https://prabhanshu.com/github), [Yashika Sharma](https://github.com/yashika51), [Kristi Takach](https://github.com/ktakattack), [Falak Shah](https://github.com/falaktheoptimist)
**Date created:** 2020/06/23
-**Last modified:** 2023/11/22
+**Last modified:** 2026/02/01
**Description:** This notebook demonstrates how to do timeseries forecasting using a LSTM model.
@@ -15,11 +15,24 @@
```python
+import os
import pandas as pd
import matplotlib.pyplot as plt
import keras
```
+
+```
+WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
+E0000 00:00:1771098579.961928 24958 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
+E0000 00:00:1771098579.966156 24958 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
+W0000 00:00:1771098579.978170 24958 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
+W0000 00:00:1771098579.978182 24958 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
+W0000 00:00:1771098579.978184 24958 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
+W0000 00:00:1771098579.978186 24958 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
+```
+
+
---
## Climate Data Time-Series
@@ -56,13 +69,18 @@ Index| Features |Format |Description
```python
+
from zipfile import ZipFile
uri = "https://storage.googleapis.com/tensorflow/tf-keras-datasets/jena_climate_2009_2016.csv.zip"
zip_path = keras.utils.get_file(origin=uri, fname="jena_climate_2009_2016.csv.zip")
zip_file = ZipFile(zip_path)
-zip_file.extractall()
-csv_path = "jena_climate_2009_2016.csv"
+
+# FIX: Extract to the cache directory, not the current working directory
+zip_file.extractall(path=os.path.dirname(zip_path))
+
+# FIX: Construct the absolute path safely (works on Windows/Linux/Mac)
+csv_path = os.path.join(os.path.dirname(zip_path), "jena_climate_2009_2016.csv")
df = pd.read_csv(csv_path)
```
@@ -190,7 +208,7 @@ past = 720
future = 72
learning_rate = 0.001
batch_size = 256
-epochs = 10
+epochs = 1
def normalize(data, train_split):
@@ -225,9 +243,9 @@ val_data = features.loc[train_split:]
```
The selected parameters are: Pressure, Temperature, Saturation vapor pressure, Vapor pressure deficit, Specific humidity, Airtight, Wind speed
-
```
+
# Training dataset
The training dataset labels starts from the 792nd observation (720 + 72).
@@ -297,9 +315,9 @@ print("Target shape:", targets.numpy().shape)
```
Input shape: (256, 120, 7)
Target shape: (256, 1)
-
```
+
---
## Training
@@ -314,27 +332,22 @@ model.compile(optimizer=keras.optimizers.Adam(learning_rate=learning_rate), loss
model.summary()
```
-
-```
-CUDA backend failed to initialize: Found cuSOLVER version 11405, but JAX was built against version 11502, which is newer. The copy of cuSOLVER that is installed must be at least as new as the version against which JAX was built. (Set TF_CPP_MIN_LOG_LEVEL=0 and rerun for more info.)
-```
-
-Model: "functional_1"
+Model: "functional"
-┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
-┃ Layer (type) ┃ Output Shape ┃ Param # ┃
-┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
-│ input_layer (InputLayer) │ (None, 120, 7) │ 0 │
-├─────────────────────────────────┼───────────────────────────┼────────────┤
-│ lstm (LSTM) │ (None, 32) │ 5,120 │
-├─────────────────────────────────┼───────────────────────────┼────────────┤
-│ dense (Dense) │ (None, 1) │ 33 │
-└─────────────────────────────────┴───────────────────────────┴────────────┘
+┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
+┃ Layer (type) ┃ Output Shape ┃ Param # ┃
+┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
+│ input_layer (InputLayer) │ (None, 120, 7) │ 0 │
+├─────────────────────────────────┼────────────────────────┼───────────────┤
+│ lstm (LSTM) │ (None, 32) │ 5,120 │
+├─────────────────────────────────┼────────────────────────┼───────────────┤
+│ dense (Dense) │ (None, 1) │ 33 │
+└─────────────────────────────────┴────────────────────────┴───────────────┘
@@ -382,51 +395,19 @@ history = model.fit(
)
```
+
```
-Epoch 1/10
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - loss: 0.3008
-Epoch 1: val_loss improved from inf to 0.15039, saving model to model_checkpoint.weights.h5
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 104s 88ms/step - loss: 0.3007 - val_loss: 0.1504
-Epoch 2/10
- 1171/1172 ━━━━━━━━━━━━━━━━━━━[37m━ 0s 66ms/step - loss: 0.1397
-Epoch 2: val_loss improved from 0.15039 to 0.14231, saving model to model_checkpoint.weights.h5
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 97s 83ms/step - loss: 0.1396 - val_loss: 0.1423
-Epoch 3/10
- 1171/1172 ━━━━━━━━━━━━━━━━━━━[37m━ 0s 69ms/step - loss: 0.1242
-Epoch 3: val_loss did not improve from 0.14231
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 101s 86ms/step - loss: 0.1242 - val_loss: 0.1513
-Epoch 4/10
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 0s 68ms/step - loss: 0.1182
-Epoch 4: val_loss did not improve from 0.14231
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 102s 87ms/step - loss: 0.1182 - val_loss: 0.1503
-Epoch 5/10
- 1171/1172 ━━━━━━━━━━━━━━━━━━━[37m━ 0s 67ms/step - loss: 0.1160
-Epoch 5: val_loss did not improve from 0.14231
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 100s 85ms/step - loss: 0.1160 - val_loss: 0.1500
-Epoch 6/10
- 1171/1172 ━━━━━━━━━━━━━━━━━━━[37m━ 0s 69ms/step - loss: 0.1130
-Epoch 6: val_loss did not improve from 0.14231
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 100s 86ms/step - loss: 0.1130 - val_loss: 0.1469
-Epoch 7/10
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 0s 70ms/step - loss: 0.1106
-Epoch 7: val_loss improved from 0.14231 to 0.13916, saving model to model_checkpoint.weights.h5
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 104s 89ms/step - loss: 0.1106 - val_loss: 0.1392
-Epoch 8/10
- 1171/1172 ━━━━━━━━━━━━━━━━━━━[37m━ 0s 66ms/step - loss: 0.1097
-Epoch 8: val_loss improved from 0.13916 to 0.13257, saving model to model_checkpoint.weights.h5
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 98s 84ms/step - loss: 0.1097 - val_loss: 0.1326
-Epoch 9/10
- 1171/1172 ━━━━━━━━━━━━━━━━━━━[37m━ 0s 68ms/step - loss: 0.1075
-Epoch 9: val_loss improved from 0.13257 to 0.13057, saving model to model_checkpoint.weights.h5
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 100s 85ms/step - loss: 0.1075 - val_loss: 0.1306
-Epoch 10/10
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 0s 66ms/step - loss: 0.1065
-Epoch 10: val_loss improved from 0.13057 to 0.12671, saving model to model_checkpoint.weights.h5
- 1172/1172 ━━━━━━━━━━━━━━━━━━━━ 98s 84ms/step - loss: 0.1065 - val_loss: 0.1267
+1172/1172 ━━━━━━━━━━━━━━━━━━━━ 0s 62ms/step - loss: 0.3293
+
+Epoch 1: val_loss improved from None to 0.15638, saving model to model_checkpoint.weights.h5
+
+Epoch 1: finished saving model to model_checkpoint.weights.h5
+1172/1172 ━━━━━━━━━━━━━━━━━━━━ 92s 78ms/step - loss: 0.1987 - val_loss: 0.1564
```
+
We can visualize the loss with the function below. After one point, the loss stops
decreasing.
@@ -495,57 +476,57 @@ for x, y in dataset_val.take(5):
)
```
+
```
- 8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step
-
+8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 6ms/step
```
-
-
+
+
+
```
- 8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step
-
+8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 9ms/step
```
-
-
+
+
+
```
- 8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step
-
+8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step
```
-
-
+
+
+
```
- 8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step
-
+8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 9ms/step
```
-
-
+
+
+
```
- 8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step
-
+8/8 ━━━━━━━━━━━━━━━━━━━━ 0s 6ms/step
```
-
-
+
+
diff --git a/examples/timeseries/timeseries_traffic_forecasting.py b/examples/timeseries/timeseries_traffic_forecasting.py
index ea66ee2131..e142ec8b06 100644
--- a/examples/timeseries/timeseries_traffic_forecasting.py
+++ b/examples/timeseries/timeseries_traffic_forecasting.py
@@ -2,7 +2,7 @@
Title: Traffic forecasting using graph neural networks and LSTM
Author: [Arash Khodadadi](https://www.linkedin.com/in/arash-khodadadi-08a02490/)
Date created: 2021/12/28
-Last modified: 2023/11/22
+Last modified: 2026/02/01
Description: This example demonstrates how to do timeseries forecasting over graphs.
Accelerator: GPU
"""
@@ -83,9 +83,13 @@
"""
url = "https://github.com/VeritasYin/STGCN_IJCAI-18/raw/master/dataset/PeMSD7_Full.zip"
-data_dir = keras.utils.get_file(origin=url, extract=True, archive_format="zip")
-data_dir = data_dir.rstrip("PeMSD7_Full.zip")
+# 1. Download and extract normally
+zip_path = keras.utils.get_file(origin=url, extract=True, archive_format="zip")
+# 2. FIX: Use os.path.dirname to safely get the folder where it was extracted
+data_dir = os.path.dirname(zip_path)
+
+# 3. Construct the paths to the inner files safely
route_distances = pd.read_csv(
os.path.join(data_dir, "PeMSD7_W_228.csv"), header=None
).to_numpy()
diff --git a/examples/timeseries/timeseries_weather_forecasting.py b/examples/timeseries/timeseries_weather_forecasting.py
index 0b30771948..ce480102d1 100644
--- a/examples/timeseries/timeseries_weather_forecasting.py
+++ b/examples/timeseries/timeseries_weather_forecasting.py
@@ -2,7 +2,7 @@
Title: Timeseries forecasting for weather prediction
Authors: [Prabhanshu Attri](https://prabhanshu.com/github), [Yashika Sharma](https://github.com/yashika51), [Kristi Takach](https://github.com/ktakattack), [Falak Shah](https://github.com/falaktheoptimist)
Date created: 2020/06/23
-Last modified: 2023/11/22
+Last modified: 2026/02/01
Description: This notebook demonstrates how to do timeseries forecasting using a LSTM model.
Accelerator: GPU
"""
@@ -10,7 +10,7 @@
"""
## Setup
"""
-
+import os
import pandas as pd
import matplotlib.pyplot as plt
import keras
@@ -50,13 +50,18 @@
15 |wd (deg) |152.3 |Wind direction in degrees
"""
+
from zipfile import ZipFile
uri = "https://storage.googleapis.com/tensorflow/tf-keras-datasets/jena_climate_2009_2016.csv.zip"
zip_path = keras.utils.get_file(origin=uri, fname="jena_climate_2009_2016.csv.zip")
zip_file = ZipFile(zip_path)
-zip_file.extractall()
-csv_path = "jena_climate_2009_2016.csv"
+
+# FIX: Extract to the cache directory, not the current working directory
+zip_file.extractall(path=os.path.dirname(zip_path))
+
+# FIX: Construct the absolute path safely (works on Windows/Linux/Mac)
+csv_path = os.path.join(os.path.dirname(zip_path), "jena_climate_2009_2016.csv")
df = pd.read_csv(csv_path)