merged

ourownstory · Aug 15, 2024 · 8f14ab9 · 8f14ab9
2 parents 96b2ca2 + a19a20e
commit 8f14ab9
Show file tree

Hide file tree

Showing 5 changed files with 583 additions and 570 deletions.
diff --git a/docs/source/tutorials/tutorial11.ipynb b/docs/source/tutorials/tutorial11.ipynb
@@ -46,9 +46,7 @@
     "from pytorch_lightning.profilers import SimpleProfiler\n",
     "\n",
     "# Configure Simple Profiler\n",
-    "trainer_config = {\n",
-    "    \"profiler\": SimpleProfiler(dirpath=\"./pl_profiling\", filename=\"simple\")\n",
-    "}"
+    "trainer_config = {\"profiler\": SimpleProfiler(dirpath=\"./pl_profiling\", filename=\"simple\")}"
    ]
   },
   {
@@ -71,12 +69,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from pytorch_lightning.profilers import AdvancedProfiler\n",
     "from pytorch_lightning.profilers import AdvancedProfiler\n",
     "\n",
     "# Configure Advanced Profiler\n",
-    "trainer_config = {\n",
-    "    \"profiler\": AdvancedProfiler(dirpath=\"./pl_profiling\", filename=\"advanced\")\n",
-    "}"
+    "trainer_config = {\"profiler\": AdvancedProfiler(dirpath=\"./pl_profiling\", filename=\"advanced\")}"
    ]
   },
   {
@@ -126,8 +123,7 @@
     "\n",
     "# Model and prediction\n",
     "m = NeuralProphet(trainer_config=trainer_config)\n",
-    "df_train, df_val = m.split_df(df, valid_p=0.2)\n",
-    "metrics = m.fit(df_train, validation_df=df_val, progress=None)"
+    "m.fit(df, learning_rate=0.1, epochs=10, batch_size=128, progress=False, minimal=True)"
    ]
   },
   {
@@ -162,9 +158,7 @@
     "from pytorch_lightning.loggers import TensorBoardLogger\n",
     "\n",
     "# Configure TensorBoard logger\n",
-    "trainer_config = {\n",
-    "    \"logger\": TensorBoardLogger(\"tb_logs\", name=\"NeuralProphet\")\n",
-    "}"
+    "trainer_config = {\"logger\": TensorBoardLogger(\"tb_logs\", name=\"NeuralProphet\")}"
    ]
   },
   {
@@ -267,6 +261,9 @@
    "source": [
     "import pandas as pd\n",
     "from neuralprophet import NeuralProphet\n",
+    "from neuralprophet import set_random_seed\n",
+    "\n",
+    "set_random_seed(42)\n",
     "\n",
     "# Load the dataset from the CSV file using pandas\n",
     "df = pd.read_csv(\"https://github.com/ourownstory/neuralprophet-data/raw/main/kaggle-energy/datasets/tutorial01.csv\")\n",

diff --git a/neuralprophet/configure.py b/neuralprophet/configure.py
@@ -208,7 +208,7 @@ def set_lr_finder_args(self, dataset_size, num_batches):
         Set the lr_finder_args.
         This is the range of learning rates to test.
         """
-        num_training = 150 + int(np.log10(100 + dataset_size) * 25)
+        num_training = 100 + int(np.log10(dataset_size) * 20)
         if num_batches < num_training:
             log.warning(
                 f"Learning rate finder: The number of batches ({num_batches}) is too small than the required number \
@@ -217,7 +217,7 @@ def set_lr_finder_args(self, dataset_size, num_batches):
             # num_training = num_batches
         self.lr_finder_args.update(
             {
-                "min_lr": 1e-6,
+                "min_lr": 1e-7,
                 "max_lr": 10,
                 "num_training": num_training,
                 "early_stop_threshold": None,

diff --git a/neuralprophet/forecaster.py b/neuralprophet/forecaster.py
@@ -2805,13 +2805,12 @@ def _train(
                 lr_finder = tuner.lr_find(
                     model=self.model,
                     train_dataloaders=train_loader,
-                    val_dataloaders=val_loader,
+                    # val_dataloaders=val_loader, # not be used, but may lead to Lightning bug if not provided
                     **self.config_train.lr_finder_args,
                 )
                 # Estimate the optimal learning rate from the loss curve
                 assert lr_finder is not None
-                _, _, lr_suggestion = utils.smooth_loss_and_suggest(lr_finder.results)
-                self.model.learning_rate = lr_suggestion
+                _, _, self.model.learning_rate = utils.smooth_loss_and_suggest(lr_finder)
             start = time.time()
             self.trainer.fit(
                 self.model,
@@ -2832,8 +2831,7 @@ def _train(
                 )
                 assert lr_finder is not None
                 # Estimate the optimal learning rate from the loss curve
-                _, _, lr_suggestion = utils.smooth_loss_and_suggest(lr_finder.results)
-                self.model.learning_rate = lr_suggestion
+                _, _, self.model.learning_rate = utils.smooth_loss_and_suggest(lr_finder)
             start = time.time()
             self.trainer.fit(
                 self.model,