freedak/timesfm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add troubleshooting section to readme file

Browse Source
This commit is contained in:
Funto-Adeyemi
2023-11-11 09:39:14 +00:00
parent 95e81c3539
commit 04a5a99b43
15 changed files with 923 additions and 979 deletions
Download Patch File Download Diff File Expand all files Collapse all files
experiments/baselines/timegpt_pipeline.py
+12 -14
View File
@@ -34,9 +34,8 @@ def get_seasonality(freq: str) -> int:
return _get_seasonality(freq, seasonalities={"D": 7})
def maybe_convert_col_to_datetime(
df: pd.DataFrame, col_name: str
) -> pd.DataFrame:
def maybe_convert_col_to_datetime(df: pd.DataFrame,
col_name: str) -> pd.DataFrame:
if not pd.api.types.is_datetime64_any_dtype(df[col_name]):
df = df.copy()
df[col_name] = pd.to_datetime(df[col_name])
@@ -64,14 +63,15 @@ def zero_pad_time_series(df, freq, min_length=36):
end=start_date,
periods=min_length - len(subset) + 1,
freq=freq, # 'MS' for month start
)[
:-1
] # Exclude the start_date itself
)[:-1] # Exclude the start_date itself
# 2c. Create padding data
padding_df = pd.DataFrame(
{"ds": padding_dates, "unique_id": unique_id, "y": 0} # Zero padding
)
padding_df = pd.DataFrame({
"ds": padding_dates,
"unique_id": unique_id,
"y": 0
} # Zero padding
)
# 2d. Combine original and padding data, and append to the list
padded_data.append(pd.concat([padding_df, subset]).sort_values("ds"))
@@ -121,8 +121,7 @@ class Forecaster:
for _, (cutoffs, train, valid) in tqdm(enumerate(splits)):
if len(valid.columns) > 3:
raise NotImplementedError(
"Cross validation with exogenous variables is not yet supported."
)
"Cross validation with exogenous variables is not yet supported.")
y_pred = self.forecast(
df=train,
h=h,
@@ -138,8 +137,7 @@ class Forecaster:
raise ValueError(
"Cross validation result produced less results than expected."
" Please verify that the frequency parameter (freq) matches your"
" series' and that there aren't any missing periods."
)
" series' and that there aren't any missing periods.")
results.append(result)
out = vertical_concat(results)
out = drop_index_if_pandas(out)
@@ -203,7 +201,7 @@ class TimeGPT(Forecaster):
all_unique_ids = df["unique_id"].unique()
all_fcst_df = []
for i in range(0, len(all_unique_ids), chunk_size):
chunk_ids = all_unique_ids[i : i + chunk_size]
chunk_ids = all_unique_ids[i:i + chunk_size]
chunk_df = df[df["unique_id"].isin(chunk_ids)]
fct_chunk_df = client.forecast(
df=chunk_df,
experiments/extended_benchmarks/run_timegpt.py
+3 -6
View File
@@ -11,7 +11,6 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Evaluation script for timegpt."""
import os
@@ -25,7 +24,6 @@ import pandas as pd
from ..baselines.timegpt_pipeline import run_timegpt
from .utils import ExperimentHandler
dataset_names = [
"m1_monthly",
"m1_quarterly",
@@ -63,7 +61,6 @@ _MODEL_NAME = flags.DEFINE_string(
)
_SAVE_DIR = flags.DEFINE_string("save_dir", "./results", "Save directory")
QUANTILES = list(np.arange(1, 10) / 10.0)
@@ -90,9 +87,9 @@ def main():
)
time_df = pd.DataFrame({"time": [total_time], "model": model_name})
fcsts_df = exp.fcst_from_level_to_quantiles(fcsts_df, model_name)
results = exp.evaluate_from_predictions(
models=[model_name], fcsts_df=fcsts_df, times_df=time_df
)
results = exp.evaluate_from_predictions(models=[model_name],
fcsts_df=fcsts_df,
times_df=time_df)
print(results, flush=True)
results_list.append(results)
results_full = pd.concat(results_list)
experiments/extended_benchmarks/run_timesfm.py
-1
View File
@@ -54,7 +54,6 @@ dataset_names = [
"hospital",
]
context_dict_v2 = {}
context_dict_v1 = {
experiments/extended_benchmarks/utils.py
+24 -36
View File
@@ -11,7 +11,6 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Forked from https://github.com/Nixtla/nixtla/blob/main/experiments/amazon-chronos/src/utils.py."""
from functools import partial
@@ -46,11 +45,9 @@ def quantile_loss(
target_col: str = "y",
) -> pd.DataFrame:
delta_y = df[models].sub(df[target_col], axis=0)
res = (
np.maximum(q * delta_y, (q - 1) * delta_y)
.groupby(df[id_col], observed=True)
.mean()
)
res = (np.maximum(q * delta_y,
(q - 1) * delta_y).groupby(df[id_col],
observed=True).mean())
res.index.name = id_col
res = res.reset_index()
return res
@@ -66,10 +63,8 @@ class ExperimentHandler:
models_dir: str = "./models",
):
if dataset not in gluonts_datasets:
raise Exception(
f"dataset {dataset} not found in gluonts "
f"available datasets: {', '.join(gluonts_datasets)}"
)
raise Exception(f"dataset {dataset} not found in gluonts "
f"available datasets: {', '.join(gluonts_datasets)}")
self.dataset = dataset
self.quantiles = quantiles
self.level = self._transform_quantiles_to_levels(quantiles)
@@ -80,10 +75,8 @@ class ExperimentHandler:
gluonts_dataset = get_dataset(self.dataset)
self.horizon = gluonts_dataset.metadata.prediction_length
if self.horizon is None:
raise Exception(
f"horizon not found for dataset {self.dataset} "
"experiment cannot be run"
)
raise Exception(f"horizon not found for dataset {self.dataset} "
"experiment cannot be run")
self.freq = gluonts_dataset.metadata.freq
# get_seasonality() returns 1 for freq='D', override this to 7. This significantly improves the accuracy of
# statistical models on datasets like m5/nn5_daily. The models like AutoARIMA/AutoETS can still set
@@ -122,9 +115,8 @@ class ExperimentHandler:
@staticmethod
def _transform_quantiles_to_levels(quantiles: List[float]) -> List[int]:
level = [
int(100 - 200 * q) for q in quantiles if q < 0.5
] # in this case mean=mediain
level = [int(100 - 200 * q) for q in quantiles if q < 0.5
] # in this case mean=mediain
level = sorted(list(set(level)))
return level
@@ -153,9 +145,8 @@ class ExperimentHandler:
last_n: int | None = None,
) -> pd.DataFrame:
with multiprocessing.Pool(os.cpu_count()) as pool: # Create a process pool
results = pool.map(
parallel_transform, zip(gluonts_dataset, repeat(last_n))
)
results = pool.map(parallel_transform, zip(gluonts_dataset,
repeat(last_n)))
df = pd.concat(results)
df = df.reset_index(drop=True)
return df
@@ -177,9 +168,8 @@ class ExperimentHandler:
def save_dataframe(self, df: pd.DataFrame, file_name: str):
df.to_csv(f"{self.results_dir}/{file_name}", index=False)
def save_results(
self, fcst_df: pd.DataFrame, total_time: float, model_name: str
):
def save_results(self, fcst_df: pd.DataFrame, total_time: float,
model_name: str):
self.save_dataframe(
fcst_df,
f"{model_name}-{self.dataset}-fcst.csv",
@@ -215,23 +205,21 @@ class ExperimentHandler:
times_df = []
for model in models:
fcst_method_df = pd.read_csv(
f"{self.results_dir}/{model}-{self.dataset}-fcst.csv"
).set_index(["unique_id", "ds"])
f"{self.results_dir}/{model}-{self.dataset}-fcst.csv").set_index(
["unique_id", "ds"])
fcsts_df.append(fcst_method_df)
time_method_df = pd.read_csv(
f"{self.results_dir}/{model}-{self.dataset}-time.csv"
)
f"{self.results_dir}/{model}-{self.dataset}-time.csv")
times_df.append(time_method_df)
fcsts_df = pd.concat(fcsts_df, axis=1).reset_index()
fcsts_df["ds"] = pd.to_datetime(fcsts_df["ds"])
times_df = pd.concat(times_df)
return self.evaluate_from_predictions(
models=models, fcsts_df=fcsts_df, times_df=times_df
)
return self.evaluate_from_predictions(models=models,
fcsts_df=fcsts_df,
times_df=times_df)
def evaluate_from_predictions(
self, models: List[str], fcsts_df: pd.DataFrame, times_df: pd.DataFrame
) -> pd.DataFrame:
def evaluate_from_predictions(self, models: List[str], fcsts_df: pd.DataFrame,
times_df: pd.DataFrame) -> pd.DataFrame:
test_df = self.test_df
train_df = self.train_df
test_df = test_df.merge(fcsts_df, how="left")
@@ -262,9 +250,9 @@ class ExperimentHandler:
eval_prob_df["metric"] = "scaled_crps"
eval_df = pd.concat([eval_df, eval_prob_df]).reset_index(drop=True)
eval_df = eval_df.groupby("metric").mean(numeric_only=True).reset_index()
eval_df = eval_df.melt(
id_vars="metric", value_name="value", var_name="model"
)
eval_df = eval_df.melt(id_vars="metric",
value_name="value",
var_name="model")
times_df.insert(0, "metric", "time")
times_df = times_df.rename(columns={"time": "value"})
eval_df = pd.concat([eval_df, times_df])