Python: векторизованная функция не применяется, если соблюдены все условия ⇐ Python

[Гость]

У меня есть векторизованное определение:

Код: Выделить всё

def selection_update_weights(df):
# Define the selections for 'Win'
selections_win = ["W & O 2.5 (both untested)", "Win (untested) & O 2.5", "Win & O 2.5 (untested)", "W & O 2.5",
"W & O 1.5 (both untested)", "Win (untested) & O 1.5", "Win & O 1.5 (untested)", "W & O 1.5",
"W & U 4.5 (both untested)", "Win (untested) & U 4.5", "Win & U 4.5 (untested)", "W & U 4.5",
"W (untested)", "W"]

# Create a boolean mask for the condition for 'Win'
mask_win = (df['selection_match'] == "no match") & \
(df['selection'].isin(selections_win)) & \
(df['result_match'] == "no match") & \
(df['result'] != 'draw')

# Apply the condition and update the 'Win' column
df.loc[mask_win, 'Win'] = df.loc[mask_win, 'predicted_score_difference'] + 0.02

# Define the selections for 'DNB'
selections_DNB = ["DNB or O 2.5 (both untested)", "DNB (untested) or O 2.5", "DNB or O 2.5 (untested)",
"DNB or O 2.5", "DNB or O 1.5 (both untested)", "DNB (untested) or O 1.5",
"DNB or O 1.5 (untested)", "DNB or O 1.5", "DNB (untested)", "DNB"]

# Create a boolean mask for the condition for 'DNB'
mask_DNB = ((df['selection_match'] == 'no match') & \
(df['selection'].isin(selections_DNB)) & \
(df['result_match'] == 'no match') & \
(df['result'] != 'draw'))

# Apply the condition and update the 'DNB' column
df.loc[mask_DNB, 'DNB'] = df.loc[mask_DNB, 'predicted_score_difference'] + 0.02

# Define the selections for O 1.5'
selections_O_1_5 = ["W & O 1.5 (both untested)", "Win (untested) & O 1.5", "Win & O 1.5 (untested)",
"W & O 1.5", "DNB or O 1.5 (both untested)", "DNB (untested) or O 1.5",
"DNB or O 1.5 (untested)", "DNB or O 1.5", "O 1.5 (untested)", "O 1.5"]

# Create a boolean mask for the condition for 'O 1.5'
mask_O_1_5 = ((df['selection_match'] == 'no match') & \
(df['selection'].isin(selections_O_1_5)) & \
(df['total_score'] < 2))

# Apply the condition and update the 'O 1.5' column
df.loc[mask_O_1_5, 'O_1_5'] = df.loc[mask_O_1_5, 'predicted_total_score'] + 0.02

# Define the selections for O 2.5'
selections_O_2_5 = ["W & O 2.5 (both untested)", "Win (untested) & O 2.5", "Win & O 2.5 (untested)",
"W & O 2.5", "DNB or O 2.5 (both untested)", "DNB (untested) or O 2.5",
"DNB or O 2.5 (untested)", "DNB or O 2.5", "O 2.5 (untested)", "O 2.5"]

# Create a boolean mask for the condition for 'O 2.5'
mask_O_2_5 = ((df['selection_match'] == 'no match') & \
(df['selection'].isin(selections_O_2_5)) & \
(df['total_score'] < 3))

# Apply the condition and update the 'O 2.5' column
df.loc[mask_O_2_5, 'O_2_5'] = df.loc[mask_O_2_5, 'predicted_total_score'] + 0.02

# Define the selections for U 4.5'
selections_U_4_5 = ["W & U 4.5 (both untested)", "Win (untested) & U 4.5", "Win & U 4.5 (untested)",
"W & U 4.5", "U 4.5 (untested)", "U 4.5"]

# Create a boolean mask for the condition for 'O 2.5'
mask_U_4_5 = ((df['selection_match'] == 'no match') & \
(df['selection'].isin(selections_U_4_5)) & \
(df['total_score'] > 4))

# Apply the condition and update the 'O 2.5' column
df.loc[mask_U_4_5, 'U_4_5'] = df.loc[mask_U_4_5, 'predicted_total_score'] - 0.02

return df

и я применяю его:

Код: Выделить всё

df = selection_update_weights(df)

Хотя у меня очень большой фрейм данных, в этом фрагменте веса ​​не обновляются. Веса обновлены частично. И я не знаю почему.

Код: Выделить всё

df.head():
home_score  away_score  total_score  score_difference  predicted_total_score  predicted_score_difference result predicted_result result_match  Win  DNB  O_1_5     O_2_5  U_4_5                  selection selection_match
44           3           3            6                 0               8.748172                    8.135116   draw             home     no match  1.1  0.7    2.0  3.000000    4.0  W & O 2.5 (both untested)        no match
50           1           0            1                 1               8.605350                    7.932909   home             home        match  1.1  0.7    2.0  8.625350    4.0  W & O 1.5 (both untested)        no match
57           1           1            2                 0               7.510030                    7.750101   draw             home     no match  1.1  0.7    2.0  7.530030    4.0  W & O 1.5 (both untested)        no match
62           0           1            1                 1               8.895045                    7.710740   away             away        match  1.1  0.7    2.0  8.915045    4.0  W & O 1.5 (both untested)        no match
85           1           0            1                 1               8.099853                    7.444815   home             home        match  1.1  0.7    2.0  8.119853    4.0  W & O 1.5 (both untested)        no match

и когда я его применяю:

Код: Выделить всё

df = selection_update_weights(df)

В идеале я должен получить

Код: Выделить всё

 home_score  away_score  total_score  score_difference  predicted_total_score  predicted_score_difference result predicted_result result_match       Win  DNB    O_1_5    O_2_5    U_4_5                       selection  selection_match
3           3            6                 0               8.748172                    8.135116   draw             home     no match  8.155116  0.7       2.0         3      4.0      W & O 2.5 (both untested)        no match
1           0            1                 1               8.605350                    7.932909   home             home        match  1.100000  0.7  8.625350  8.625350      4.0      W & O 1.5 (both untested)        no match
1           1            2                 0               7.510030                    7.750101   draw             home     no match  7.770101  0.7       2.0  7.530030      4.0      W & O 1.5 (both untested)        no match
0           1            1                 1               8.895045                    7.710740   away             away        match  1.100000  0.7  8.915045  8.915045      4.0      W & O 1.5 (both untested)        no match
1           0            1                 1               8.099853                    7.444815   home             home        match  1.100000  0.7  8.119853  8.119853      4.0      W & O 1.5 (both untested)        no match

Однако этого не происходит, и исходный фрейм данных не затрагивается.
Поможет ли мне разбить каждое if-else, но фрейм данных слишком велик, а вычисления строк занимают 20 минут

Подробнее здесь: https://stackoverflow.com/questions/781 ... ns-are-met