Specify numeric_only for pandas.core.groupby.DataFrameGroupBy.mean.

This parameter used to be None by default, but this usage is deprecated since pandas 2.0.
See [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.core.groupby.DataFrameGroupBy.mean.html):

> Changed in version 2.0.0: numeric_only no longer accepts None and defaults to False.
update_libs
junos 2023-04-12 16:05:58 +02:00
parent d678be0641
commit 1d903f3629
3 changed files with 6 additions and 6 deletions

View File

@ -15,13 +15,13 @@ def extract_second_order_features(intraday_features, so_features_names, prefix="
so_features = pd.DataFrame() so_features = pd.DataFrame()
#print(intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).nsmallest()) #print(intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).nsmallest())
if "mean" in so_features_names: if "mean" in so_features_names:
so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).mean().add_suffix("_SO_mean")], axis=1) so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).mean(numeric_only=True).add_suffix("_SO_mean")], axis=1)
if "median" in so_features_names: if "median" in so_features_names:
so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).median().add_suffix("_SO_median")], axis=1) so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).median(numeric_only=True).add_suffix("_SO_median")], axis=1)
if "sd" in so_features_names: if "sd" in so_features_names:
so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).std().fillna(0).add_suffix("_SO_sd")], axis=1) so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).std(numeric_only=True).fillna(0).add_suffix("_SO_sd")], axis=1)
if "nlargest" in so_features_names: # largest 5 -- maybe there is a faster groupby solution? if "nlargest" in so_features_names: # largest 5 -- maybe there is a faster groupby solution?
for column in intraday_features.loc[:, ~intraday_features.columns.isin(groupby_cols+[prefix+"level_1"])]: for column in intraday_features.loc[:, ~intraday_features.columns.isin(groupby_cols+[prefix+"level_1"])]:

View File

@ -26,7 +26,7 @@ def calculate_empatica_data_yield(features): # TODO
# Assigns 1 to values that are over 1 (in case of windows not being filled fully) # Assigns 1 to values that are over 1 (in case of windows not being filled fully)
features[empatica_data_yield_cols] = features[empatica_data_yield_cols].apply(lambda x: [y if y <= 1 or np.isnan(y) else 1 for y in x]) features[empatica_data_yield_cols] = features[empatica_data_yield_cols].apply(lambda x: [y if y <= 1 or np.isnan(y) else 1 for y in x])
features["empatica_data_yield"] = features[empatica_data_yield_cols].mean(axis=1).fillna(0) features["empatica_data_yield"] = features[empatica_data_yield_cols].mean(axis=1, numeric_only=True).fillna(0)
features.drop(empatica_data_yield_cols, axis=1, inplace=True) # In case of if the advanced operations will later not be needed (e.g., weighted average) features.drop(empatica_data_yield_cols, axis=1, inplace=True) # In case of if the advanced operations will later not be needed (e.g., weighted average)
return features return features

View File

@ -140,8 +140,8 @@ def extract_ers(esm_df):
# Extracted 3 targets that will be transfered in the csv file to the cleaning script. # Extracted 3 targets that will be transfered in the csv file to the cleaning script.
se_stressfulness_event_tg = esm_df[esm_df.questionnaire_id == 87.].set_index(['device_id', 'esm_session'])['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_stressfulness_event'}) se_stressfulness_event_tg = esm_df[esm_df.questionnaire_id == 87.].set_index(['device_id', 'esm_session'])['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_stressfulness_event'})
se_threat_tg = esm_df[esm_df.questionnaire_id == 88.].groupby(["device_id", "esm_session"]).mean()['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_threat'}) se_threat_tg = esm_df[esm_df.questionnaire_id == 88.].groupby(["device_id", "esm_session"]).mean(numeric_only=True)['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_threat'})
se_challenge_tg = esm_df[esm_df.questionnaire_id == 89.].groupby(["device_id", "esm_session"]).mean()['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_challenge'}) se_challenge_tg = esm_df[esm_df.questionnaire_id == 89.].groupby(["device_id", "esm_session"]).mean(numeric_only=True)['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_challenge'})
# All relevant features are joined by inner join to remove standalone columns (e.g., stressfulness event target has larger count) # All relevant features are joined by inner join to remove standalone columns (e.g., stressfulness event target has larger count)
extracted_ers = extracted_ers.join(session_start_timestamp, on=['device_id', 'esm_session'], how='inner') \ extracted_ers = extracted_ers.join(session_start_timestamp, on=['device_id', 'esm_session'], how='inner') \