def test_evaluator_df_preds_with_scaling_not_equal_without_scaling(self):
inference_params = {
"datetime_start": datetime.datetime(2016, 5, 31, 0),
"hours_to_forecast": 336,
"dataset_params": self.data_base_params,
"test_csv_path": os.path.join(self.test_path2, "keag_small.csv"),
"num_prediction_samples": 10,
}
inference_params_with_scaling = {
"datetime_start": datetime.datetime(2016, 5, 31, 0),
"hours_to_forecast": 336,
"dataset_params": self.data_base_params_with_scaling,
"test_csv_path": os.path.join(self.test_path2, "keag_small.csv"),
"num_prediction_samples": 10,
}
model_result_1 = evaluate_model(
self.model, "PyTorch", ["cfs"], ["MSE", "L1"], inference_params, {}
)
model_result_2 = evaluate_model(
self.model,
"PyTorch",
["cfs"],
["MSE", "L1"],
inference_params_with_scaling,
{},
)
self.assertFalse(model_result_1[3].equals(model_result_2[3]))
def train_function(model_type: str, params:Dict):
"""
Function to train a Model(TimeSeriesModel) or da_rnn. Will return the trained model
model_type str: Type of the model (for now) must be da_rnn or
:params dict: Dictionary containing all the parameters needed to run the model
"""
dataset_params = params["dataset_params"]
if model_type == "da_rnn":
from flood_forecast.da_rnn.train_da import da_rnn, train
from flood_forecast.preprocessing.preprocess_da_rnn import make_data
preprocessed_data = make_data(params["dataset_params"]["training_path"], params["dataset_params"]["target_col"], params["dataset_params"]["forecast_length"])
config, model = da_rnn(preprocessed_data, len(dataset_params["target_col"]))
# All train functions return trained_model
trained_model = train(model, preprocessed_data, config)
elif model_type == "PyTorch":
trained_model = PyTorchForecast(
params["model_name"],
dataset_params["training_path"],
dataset_params["validation_path"],
dataset_params["test_path"],
params)
train_transformer_style(trained_model, params["training_params"], params["forward_params"])
params["inference_params"]["dataset_params"]["scaling"] = scaler_dict[dataset_params["scaler"]]
test_acc = evaluate_model(
trained_model,
model_type,
params["dataset_params"]["target_col"],
params["metrics"],
params["inference_params"],
{})
wandb.run.summary["test_accuracy"] = test_acc[0]
df_train_and_test = test_acc[1]
forecast_start_idx = test_acc[2]
df_prediction_samples = test_acc[3]
inverse_mae = 1 / (
df_train_and_test.loc[forecast_start_idx:, "preds"] -
df_train_and_test.loc[forecast_start_idx:, params["dataset_params"]["target_col"][0]]).abs()
pred_std = df_prediction_samples.std(axis=1)
average_prediction_sharpe = (inverse_mae / pred_std).mean()
wandb.log({'average_prediction_sharpe': average_prediction_sharpe})
# Log plots
test_plot = plot_df_test_with_confidence_interval(
df_train_and_test,
df_prediction_samples,
forecast_start_idx,
params,
ci=95,
alpha=0.25)
wandb.log({"test_plot": test_plot})
test_plot_all = go.Figure()
for relevant_col in params["dataset_params"]["relevant_cols"]:
test_plot_all.add_trace(go.Scatter(x=df_train_and_test.index, y=df_train_and_test[relevant_col], name=relevant_col))
wandb.log({"test_plot_all": test_plot_all})
else:
raise Exception("Please supply valid model type for forecasting")
return trained_model
def test_evaluator(self):
inference_params = {
"datetime_start": datetime.datetime(2016, 5, 31, 0),
"hours_to_forecast": 336,
"dataset_params": self.data_base_params,
"test_csv_path": os.path.join(self.test_path2, "keag_small.csv")
}
model_result = evaluate_model(self.model, "PyTorch", ["cfs"],
["MSE", "L1"], inference_params, {})
self.assertGreater(model_result[0]["cfs_L1"], 0)
self.assertGreater(model_result[0]["cfs_MSE"], 1)
def test_evaluator_generate_prediction_samples(self):
inference_params = {
"datetime_start": datetime.datetime(2016, 5, 31, 0),
"hours_to_forecast": 336,
"dataset_params": self.data_base_params,
"test_csv_path": os.path.join(self.test_path2, "keag_small.csv"),
"num_prediction_samples": 100,
}
model_result = evaluate_model(
self.model, "PyTorch", ["cfs"], ["MSE", "L1"], inference_params, {}
)
df_train_and_test = model_result[1]
df_prediction_samples = model_result[3]
self.assertTrue(df_train_and_test.index.equals(df_prediction_samples.index))
self.assertEqual(100, df_prediction_samples.shape[1])
def test_evaluator(self):
inference_params = {
"datetime_start": datetime.datetime(2016, 5, 31, 0),
"hours_to_forecast": 336,
"dataset_params": self.data_base_params,
"test_csv_path": os.path.join(self.test_path2, "keag_small.csv"),
}
model_result = evaluate_model(self.model, "PyTorch", ["cfs"],
["MSE", "L1"], inference_params, {})
print(model_result)
eval_dict = model_result[0]
self.assertGreater(eval_dict["cfs_MAPELoss"], 0)
self.assertGreater(eval_dict["cfs_MSELoss"], 420)
# self.assertNotAlmostEqual(eval_dict["cfs_MAPELoss"], eval_dict["cfs_MSELoss"])
self.assertLessEqual(eval_dict["cfs_MAPELoss"].item(), 400)
def train_function(model_type: str, params: Dict):
"""Function to train a Model(TimeSeriesModel) or da_rnn. Will return the trained model
:param model_type: Type of the model. In almost all cases this will be 'PyTorch'
:type model_type: str
:param params: Dictionary containing all the parameters needed to run the model
:type Dict:
"""
dataset_params = params["dataset_params"]
if model_type == "da_rnn":
from flood_forecast.da_rnn.train_da import da_rnn, train
from flood_forecast.preprocessing.preprocess_da_rnn import make_data
preprocessed_data = make_data(
params["dataset_params"]["training_path"],
params["dataset_params"]["target_col"],
params["dataset_params"]["forecast_length"])
config, model = da_rnn(preprocessed_data,
len(dataset_params["target_col"]))
# All train functions return trained_model
trained_model = train(model, preprocessed_data, config)
elif model_type == "PyTorch":
trained_model = PyTorchForecast(params["model_name"],
dataset_params["training_path"],
dataset_params["validation_path"],
dataset_params["test_path"], params)
takes_target = False
if "takes_target" in trained_model.params:
takes_target = trained_model.params["takes_target"]
train_transformer_style(model=trained_model,
training_params=params["training_params"],
takes_target=takes_target,
forward_params=params["forward_params"])
# To do delete
if "scaler" in dataset_params:
if "scaler_params" in dataset_params:
params["inference_params"]["dataset_params"][
"scaling"] = scaling_function({},
dataset_params)["scaling"]
else:
params["inference_params"]["dataset_params"][
"scaling"] = scaling_function({},
dataset_params)["scaling"]
params["inference_params"]["dataset_params"].pop(
'scaler_params', None)
test_acc = evaluate_model(trained_model, model_type,
params["dataset_params"]["target_col"],
params["metrics"],
params["inference_params"], {})
wandb.run.summary["test_accuracy"] = test_acc[0]
df_train_and_test = test_acc[1]
forecast_start_idx = test_acc[2]
df_prediction_samples = test_acc[3]
mae = (df_train_and_test.loc[forecast_start_idx:, "preds"] -
df_train_and_test.loc[forecast_start_idx:,
params["dataset_params"]["target_col"][0]]
).abs()
inverse_mae = 1 / mae
i = 0
for df in df_prediction_samples:
pred_std = df.std(axis=1)
average_prediction_sharpe = (inverse_mae / pred_std).mean()
wandb.log({
'average_prediction_sharpe' + str(i):
average_prediction_sharpe
})
i += 1
df_train_and_test.to_csv("temp_preds.csv")
# Log plots now
if "probabilistic" in params["inference_params"]:
test_plot = plot_df_test_with_probabilistic_confidence_interval(
df_train_and_test,
forecast_start_idx,
params,
)
elif len(df_prediction_samples) > 0:
for thing in zip(df_prediction_samples,
params["dataset_params"]["target_col"]):
thing[0].to_csv(thing[1] + ".csv")
test_plot = plot_df_test_with_confidence_interval(
df_train_and_test,
thing[0],
forecast_start_idx,
params,
targ_col=thing[1],
ci=95,
alpha=0.25)
wandb.log({"test_plot_" + thing[1]: test_plot})
else:
pd.options.plotting.backend = "plotly"
t = params["dataset_params"]["target_col"][0]
test_plot = df_train_and_test[[t, "preds"]].plot()
wandb.log({"test_plot_" + t: test_plot})
print("Now plotting final plots")
test_plot_all = go.Figure()
for relevant_col in params["dataset_params"]["relevant_cols"]:
test_plot_all.add_trace(
go.Scatter(x=df_train_and_test.index,
y=df_train_and_test[relevant_col],
name=relevant_col))
wandb.log({"test_plot_all": test_plot_all})
else:
raise Exception("Please supply valid model type for forecasting")
return trained_model
def handle_model_evaluation1(trained_model, params: Dict,
model_type: str) -> None:
"""Utility function to help handle model evaluation. Primarily used at the moment for forcast
:param trained_model: A PyTorchForecast model that has already been trained.
:type trained_model: PyTorchForecast
:param params: A dictionary of the trained model parameters.
:type params: Dict
:param model_type: The type of model. Almost always PyTorch in practice.
:type model_type: str
"""
test_acc = evaluate_model(trained_model, model_type,
params["dataset_params"]["target_col"],
params["metrics"], params["inference_params"],
{})
wandb.run.summary["test_accuracy"] = test_acc[0]
df_train_and_test = test_acc[1]
forecast_start_idx = test_acc[2]
df_prediction_samples = test_acc[3]
mae = (df_train_and_test.loc[forecast_start_idx:, "preds"] -
df_train_and_test.loc[forecast_start_idx:,
params["dataset_params"]["target_col"][0]]
).abs()
inverse_mae = 1 / mae
i = 0
for df in df_prediction_samples:
pred_std = df.std(axis=1)
average_prediction_sharpe = (inverse_mae / pred_std).mean()
wandb.log(
{'average_prediction_sharpe' + str(i): average_prediction_sharpe})
i += 1
df_train_and_test.to_csv("temp_preds.csv")
# Log plots now
if "probabilistic" in params["inference_params"]:
test_plot = plot_df_test_with_probabilistic_confidence_interval(
df_train_and_test,
forecast_start_idx,
params,
)
elif len(df_prediction_samples) > 0:
for thing in zip(df_prediction_samples,
params["dataset_params"]["target_col"]):
thing[0].to_csv(thing[1] + ".csv")
test_plot = plot_df_test_with_confidence_interval(
df_train_and_test,
thing[0],
forecast_start_idx,
params,
targ_col=thing[1],
ci=95,
alpha=0.25)
wandb.log({"test_plot_" + thing[1]: test_plot})
else:
pd.options.plotting.backend = "plotly"
t = params["dataset_params"]["target_col"][0]
test_plot = df_train_and_test[[t, "preds"]].plot()
wandb.log({"test_plot_" + t: test_plot})
print("Now plotting final plots")
test_plot_all = go.Figure()
for relevant_col in params["dataset_params"]["relevant_cols"]:
test_plot_all.add_trace(
go.Scatter(x=df_train_and_test.index,
y=df_train_and_test[relevant_col],
name=relevant_col))
wandb.log({"test_plot_all": test_plot_all})
