End-to-End-Time-Series icon indicating copy to clipboard operation
End-to-End-Time-Series copied to clipboard

Deprecation warning about DataFrame index on "Timeseries_Data_analysis.ipynb"

Open guillempuche opened this issue 3 years ago • 1 comments

Warning: imatge

You have to change lines:

  • aq_df_2016=aq_df['2016'] for aq_df_2016=aq_df.loc['2016']
  • df_2014= aq_df['2014'].reset_index() for df_2014= aq_df.loc['2014'].reset_index()
  • df_2015 = aq_df['2015'].reset_index() for df_2015 = aq_df.loc['2015'].reset_index()
  • On several lines aq_df_2015=aq_df['2015'] for aq_df_2015=aq_df.loc['2015']

I'm using:

  • pandas 1.2.3
  • python 3.8.8

guillempuche avatar Apr 11 '21 10:04 guillempuche

Thanks will make the changes and I modified my code and ran it on fit instead of fit_generator with TF2.5 and it works

early_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=2, mode='min')

model.compile(loss=tf.losses.MeanSquaredError(), optimizer=tf.optimizers.Adam(), metrics=[tf.metrics.MeanAbsoluteError()])

history = model.fit(train_generator, epochs=20, validation_data=val_generator, shuffle=False, callbacks=[early_stopping])

Will upload it once I add additional details to it

srivatsan88 avatar Jun 10 '21 13:06 srivatsan88