bs/Step_Data_Project_India
0
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

added differentiation between 3 different models

Browse Source
This commit is contained in:
bs
2025-09-04 13:43:38 +02:00
parent 65dac044d7
commit b1b63d416d
3 changed files with 63 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main.py
+39 -31
View File
@@ -12,8 +12,7 @@ from pipeline import (
prepare_user_data,
train_models,
evaluate_models,
display_warning_about_2020_data,
display_warnings_for_scenarios, prepare_data_for_model
prepare_data_for_model, model_type_gru, model_type_lstm, model_type_bilstm
)
year_str = 'Year'
@@ -26,6 +25,7 @@ sequence_length_str = 'sequence length'
precision_str = 'precision'
recall_str = 'recall'
f1_string = 'f1 score'
model_type_str = 'model type'
weak_column_names = ['DayOfWeek_'+day for day in
['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday' ]]
@@ -34,7 +34,7 @@ dataset_path = './Datasets/'
DATA_PATH = dataset_path +'ALLUSERS32_15MIN_WITHOUTTHREHOLD.xlsx'
OUTPUT_EXCEL_PATH = './working/evaluation_results.xlsx'
result_filename = './working/evaluation_results.json'
SEQUENCE_LENGTHS = [20, 15, 10, 5, 1] # You can add more: [20, 25, 30]
SEQUENCE_LENGTHS = [30, 25, 20, 15, 10, 5] # You can add more: [20, 25, 30]
TRAINING_SCENARIO = [(2018, list(range(1, 13))), (2019, list(range(1, 10)))]
VALIDATION_SCENARIO = [(2019, [10, 11, 12])]
@@ -117,40 +117,47 @@ def main_two():
for sequence_length in SEQUENCE_LENGTHS:
for data_filename in os.listdir(dataset_path):
for split_id, split_method in [('data percentages', split_data_by_userdata_percentage),('month percentages', split_data_by_month_percentage)]:
timespan_id = '1HR'
threshold_id = 'WITH'
if '15MIN' in data_filename:
timespan_id = '15MIN'
if 'WITHOUT' in data_filename:
threshold_id = 'WITHOUT'
if len(results) > 0:
if len(results[(results[split_str]==split_id) &
(results[timespan_str]==timespan_id) &
(results[threshold_str]==threshold_id) &
(results[sequence_length_str]==sequence_length)]) > 0:
continue
for model_type in [model_type_lstm, model_type_bilstm, model_type_gru]:
timespan_id = '1HR'
threshold_id = 'WITH'
if '15MIN' in data_filename:
timespan_id = '15MIN'
if 'WITHOUT' in data_filename:
threshold_id = 'WITHOUT'
if len(results) > 0:
if len(results[(results[split_str]==split_id) &
(results[timespan_str]==timespan_id) &
(results[threshold_str]==threshold_id) &
(results[sequence_length_str]==sequence_length) &
(results[model_type_str]==model_type)]) > 0:
continue
file_path = os.path.join(dataset_path, data_filename)
df = load_dataset(file_path)
df = remove_covid_data(df)
tr,val,te = split_method(df, percentages=(80,10,10))
tr = reduce_columns(tr, data_filename)
val = reduce_columns(val, data_filename)
te = reduce_columns(te, data_filename)
file_path = os.path.join(dataset_path, data_filename)
df = load_dataset(file_path)
df = remove_covid_data(df)
df = df.head(1000) # TODO: remove
tr,val,te = split_method(df, percentages=(80,10,10))
tr = reduce_columns(tr, data_filename)
val = reduce_columns(val, data_filename)
te = reduce_columns(te, data_filename)
user_data_train = prepare_user_data(tr)
user_data_val = prepare_user_data(val)
user_data_train = prepare_user_data(tr)
user_data_val = prepare_user_data(val)
best_models = train_models(user_data_train, user_data_val, sequence_lengths=[sequence_length])
best_models = train_models(user_data_train, user_data_val, sequence_lengths=[sequence_length], model_type=model_type)
results = pd.concat([results,
evaluate_model_on_test_data(model=best_models[sequence_length]['model'], test_df=te, split_id=split_id,
sequence_length=sequence_length, time_span_id=timespan_id, threshold_id=threshold_id)], ignore_index=True)
results.to_json(result_filename)
results = pd.concat([results,
evaluate_model_on_test_data(model=best_models[sequence_length]['model'],
test_df=te, split_id=split_id,
sequence_length=sequence_length,
time_span_id=timespan_id,
threshold_id=threshold_id,
model_type=model_type)], ignore_index=True)
results.to_json(result_filename)
# === Evaluation ===
def evaluate_model_on_test_data(model, test_df,sequence_length, split_id, threshold_id, time_span_id):
def evaluate_model_on_test_data(model, test_df,sequence_length, split_id, threshold_id, time_span_id, model_type):
user_data = prepare_user_data(test_df)
x, y = prepare_data_for_model(user_data=user_data, sequence_length=sequence_length)
@@ -161,7 +168,8 @@ def evaluate_model_on_test_data(model, test_df,sequence_length, split_id, thresh
precision = sklearn.metrics.precision_score(y, y_pred_classes, average='weighted')
f1_score = sklearn.metrics.f1_score(y, y_pred_classes, average='weighted')
return pd.DataFrame({split_str:[split_id], threshold_str:[threshold_id], timespan_str:[time_span_id],
sequence_length_str:[sequence_length], recall_str:[recall],
sequence_length_str:[sequence_length],
model_type_str:[model_type], recall_str:[recall],
precision_str:[precision], f1_string:[f1_score]})