I'm trying to import KerasClassifier into VScode but i keep getting this error
ModuleNotFoundError Traceback (most recent call last) Cell In[7], line 1 1 from tensorflow.keras.wrappers.scikit_learn import KerasClassifier
ModuleNotFoundError: No module named 'tensorflow.keras.wrappers'
Does anyone know a way to fix it or another way around it? Here's my full code for context:
import pandas as pd
import re
from sklearn.model_selection import GridSearchCV
import numpy as np
import datetime
from pandas.tseries.offsets import MonthEnd
from sklearn.preprocessing import MinMaxScaler, LabelEncoder
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, LSTM
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.wrappers.scikit_learn import KerasClassifier
df = pd.read_csv('Billing_Report_w_Revshare Calc.csv')
df['Date'] = pd.to_datetime(df['Date'])
df['Date'] = df['Date'].apply(lambda dt: dt.replace(day=30) if dt.month == 6 else dt)
df = df.dropna(subset=['Domain'])
def modify_url_suffix(url):
pattern = r'\.(?!net|co|org|news|tv|pr|us|edu)([a-z]+)$'
modified_url = re.sub(pattern, '.com', url, flags=re.I)
return modified_url
df['Domain'] = df['Domain'].apply(modify_url_suffix)
df = df[['Date', 'Domain', 'DFP Group Code', 'Program Code', 'Total Agency Ad Requests',
'Total Agency Impressions', 'Total DFP Impressions', 'Reporting Impressions', 'Total Rev',
'Total Active View eligible impressions', 'Total Active View measurable impressions',
'Total Active View viewable impressions', 'Customer Rev Share']]
df = df[df['Date'] > '2017-04-01']
df['Customer Rev Share'] = df['Customer Rev Share'].abs()
df = df.groupby(['Date', 'Domain', 'DFP Group Code', 'Program Code']).sum().reset_index()
def calculate_net_cpm(row):
try:
return round((row['Total Rev'] * 1000 / row['Total Agency Impressions']) * 0.78, 2)
except (ZeroDivisionError, Exception):
return 0
df['net_cpm'] = df.apply(calculate_net_cpm, axis=1)
last_day_previous_month = pd.to_datetime('today') - pd.tseries.offsets.MonthEnd(1)
previous_month_year = last_day_previous_month.year
previous_month_month = last_day_previous_month.month
df_previous_month = df[(df['Date'].dt.year == previous_month_year) & (df['Date'].dt.month == previous_month_month)]
previous_month_domains = df_previous_month['Domain'].unique()
df = df[df['Domain'].isin(previous_month_domains)]
yup_df = df.loc[(df['Program Code'] == 'YUP') & (df['Date'].dt.year == previous_month_year) & (df['Date'].dt.month == previous_month_month)]
yup_df = yup_df[['Domain']]
df = df[df['Domain'].isin(yup_df['Domain'])]
df = df.sort_values(['Domain', 'Date'])
df = df[['Date', 'Domain', 'Total Agency Ad Requests',
'Total Agency Impressions', 'Total DFP Impressions', 'Reporting Impressions', 'Total Rev',
'Total Active View eligible impressions', 'Total Active View measurable impressions',
'Total Active View viewable impressions', 'Customer Rev Share', 'net_cpm']]
count_per_domain = df['Domain'].value_counts()
sufficient_data_domains = count_per_domain[count_per_domain > 4].index
df_sufficient_data = df[df['Domain'].isin(sufficient_data_domains)]
df_insufficient_data = df[~df['Domain'].isin(sufficient_data_domains)]
df_sufficient_data = df_sufficient_data.sort_values(['Domain', 'Date'], ascending=[True, True])
feature_scaler = MinMaxScaler()
numeric_columns = ['Total Agency Ad Requests', 'Total Agency Impressions', 'Total DFP Impressions',
'Reporting Impressions', 'Total Rev', 'Total Active View eligible impressions',
'Total Active View measurable impressions', 'Total Active View viewable impressions',
'Customer Rev Share']
df_sufficient_data[numeric_columns] = feature_scaler.fit_transform(df_sufficient_data[numeric_columns])
time_steps = 5
def reshape_to_3d(arr, time_steps):
x = []
for i in range(len(arr) - time_steps):
x.append(arr[i: (i + time_steps)])
return np.array(x)
X = []
y = []
encoder = LabelEncoder()
encoder.fit(df_sufficient_data['net_cpm'])
num_classes = len(encoder.classes_)
for domain in df_sufficient_data['Domain'].unique():
domain_data = df_sufficient_data[df_sufficient_data['Domain'] == domain]
domain_data = domain_data.drop(['Date', 'Domain'], axis=1)
domain_data[numeric_columns] = feature_scaler.transform(domain_data[numeric_columns])
encoded_y = encoder.transform(domain_data['net_cpm'])
dummy_y = to_categorical(encoded_y, num_classes=num_classes)
X_domain = domain_data.drop('net_cpm', axis=1).values
X_domain_3d = reshape_to_3d(X_domain, time_steps)
y_domain = dummy_y[time_steps:]
if X_domain_3d.ndim == 3 and y_domain.ndim == 2:
X.append(X_domain_3d)
y.append(y_domain)
X = np.concatenate(X)
y = np.concatenate(y)
print("Shape of X:", X.shape)
print("Shape of y:", y.shape)
def create_model(lstm_units=50, learning_rate=0.01):
model = Sequential()
model.add(LSTM(lstm_units, activation='relu', input_shape=(5, 9)))
model.add(Dense(580, activation='softmax'))
optimizer = Adam(learning_rate=learning_rate)
model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])
return model
model = KerasClassifier(build_fn=create_model, epochs=10, batch_size=32, verbose=1)
param_grid = {'lstm_units': [30, 50, 70], 'learning_rate': [0.001, 0.01, 0.1]}
grid = GridSearchCV(estimator=model, param_grid=param_grid, n_jobs=-1, cv=3)
grid_result = grid.fit(X, y)
print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
final_model = create_model(lstm_units=grid_result.best_params_['lstm_units'], learning_rate=grid_result.best_params_['learning_rate'])
final_model.fit(X, y, epochs=10, batch_size=32, validation_split=0.2)
I've tried creating my own custom wrapper but i'm having issues with that.
