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

Minimal Code clean up

Browse Source
This commit is contained in:
bs
2026-01-21 10:04:07 +01:00
parent b01cd988e6
commit 1d14bc0c8d
4 changed files with 31 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pipeline.py
+13 -15
View File
@@ -68,33 +68,34 @@ def prepare_user_data(df):
def make_sequences(data, sequence_length):
x, y = [], []
features = data.drop('user', axis=1).values
#features = features.astype(int)
labels = data['user'].values
for i in range(len(features) - sequence_length+1):
# for i in range(len(features) - sequence_length+1): # with overlap on days
for i in range(0, len(features) - sequence_length + 1, sequence_length): # without overlap on days
x.append(features[i:i + sequence_length])
y.append(labels[i + sequence_length-1])
return x, y
def prepare_data_for_model(user_data, sequence_length):
def prepare_data_for_model(user_data, sequence_length, print_counts=False):
x, y = [], []
combined = pd.DataFrame()
for user, data in user_data.items():
x_new, y_new = make_sequences(data, sequence_length)
x = x + x_new
y = y + y_new
if len(x_new)>0:
if print_counts and len(x_new)>0:
var = [[pd.DataFrame(a[s])for s in range(sequence_length)] for a in x_new ]
df_var = pd.concat([pd.concat(seq_list).T for seq_list in var])
df_var['user'] = user
combined = pd.concat([combined, df_var], ignore_index=True)
combined_ohne = combined.drop('user', axis=1)
print('Alle', len(combined))
print('Unique mit user', len(combined.drop_duplicates()))
print('Unique ohne user', len(combined_ohne.drop_duplicates()))
print('Unique')
print(combined.drop_duplicates()['user'].value_counts())
print('Alle')
print(combined['user'].value_counts())
if print_counts:
combined_ohne = combined.drop('user', axis=1)
print('Alle', len(combined))
print('Unique mit user', len(combined.drop_duplicates()))
print('Unique ohne user', len(combined_ohne.drop_duplicates()))
print('Unique')
print(combined.drop_duplicates()['user'].value_counts())
print('Alle')
print(combined['user'].value_counts())
random.Random(17).shuffle(x)
random.Random(17).shuffle(y)
x = np.array(x)
@@ -239,11 +240,8 @@ def train_one_model(train_data, val_data, n_batch, n_epochs, n_neurons,n_neurons
# model.add(LSTM(n_neurons, kernel_regularizer=reg1, return_sequences=True))
model.add(LSTM(n_neurons))
# model.add(LSTM(n_neurons2))
# model.add(LSTM(n_neurons3, return_sequences=True))
# model.add(LSTM(n_neurons4))
if model_type == model_type_gru:
model.add(GRU(n_neurons))
# TODO: add another dense layer
#model.add(Dense(n_neurons, activation='relu'))
#model.add(Dropout(d1))
model.add(Dense(len(users), activation='softmax'))