Skip to content

Instantly share code, notes, and snippets.

@slaporte
Created October 21, 2012 19:17
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save slaporte/3928159 to your computer and use it in GitHub Desktop.
Save slaporte/3928159 to your computer and use it in GitHub Desktop.
media_attrs = ['d_all_img_count',
'd_geo_count',
'd_image_map_count',
'd_ipa_count',
'd_midi_count',
'd_ogg_count',
'd_pdf_count',
'd_spoken_wp_count',
'd_svg_count',
'd_tex_count',
'd_thumb_img_count',
'd_thumb_left_count',
'd_thumb_right_count']
formatting_attrs = ['d_blockquote_count',
'd_caption_word_count',
'd_caption_word_kurtosis',
'd_caption_word_kurtosis_trimmed',
'd_caption_word_mean',
'd_caption_word_mean_trimmed',
'd_caption_word_median',
'd_caption_word_median_abs_dev',
'd_caption_word_rel_std_dev',
'd_caption_word_skewness',
'd_caption_word_skewness_trimmed',
'd_caption_word_std_dev',
'd_caption_word_std_dev_trimmed',
'd_caption_word_variance',
'd_p_kurtosis',
'd_p_kurtosis_trimmed',
'd_p_mean',
'd_p_mean_trimmed',
'd_p_median',
'd_p_median_abs_dev',
'd_p_rel_std_dev',
'd_p_skewness',
'd_p_skewness_trimmed',
'd_p_std_dev',
'd_p_std_dev_trimmed',
'd_p_variance',
'd_wiki_file_link_count',
'd_wikitable_word_count',
'd_wikitable_word_kurtosis',
'd_wikitable_word_kurtosis_trimmed',
'd_wikitable_word_mean',
'd_wikitable_word_mean_trimmed',
'd_wikitable_word_median',
'd_wikitable_word_median_abs_dev',
'd_wikitable_word_rel_std_dev',
'd_wikitable_word_skewness',
'd_wikitable_word_skewness_trimmed',
'd_wikitable_word_std_dev',
'd_wikitable_word_std_dev_trimmed',
'd_wikitable_word_variance',
]
structure_attrs = ['d_h2_header_count',
'd_h2_header_kurtosis',
'd_h2_header_kurtosis_trimmed',
'd_h2_header_mean',
'd_h2_header_mean_trimmed',
'd_h2_header_median',
'd_h2_header_median_abs_dev',
'd_h2_header_rel_std_dev',
'd_h2_header_skewness',
'd_h2_header_skewness_trimmed',
'd_h2_header_std_dev',
'd_h2_header_std_dev_trimmed',
'd_h2_header_variance',
'd_h2_text_count',
'd_h2_text_kurtosis',
'd_h2_text_kurtosis_trimmed',
'd_h2_text_mean',
'd_h2_text_mean_trimmed',
'd_h2_text_median',
'd_h2_text_median_abs_dev',
'd_h2_text_rel_std_dev',
'd_h2_text_skewness',
'd_h2_text_skewness_trimmed',
'd_h2_text_std_dev',
'd_h2_text_std_dev_trimmed',
'd_h2_text_variance',
'd_h3_header_count',
'd_h3_header_kurtosis',
'd_h3_header_kurtosis_trimmed',
'd_h3_header_mean',
'd_h3_header_mean_trimmed',
'd_h3_header_median',
'd_h3_header_median_abs_dev',
'd_h3_header_rel_std_dev',
'd_h3_header_skewness',
'd_h3_header_skewness_trimmed',
'd_h3_header_std_dev',
'd_h3_header_std_dev_trimmed',
'd_h3_header_variance',
'd_h3_text_count',
'd_h3_text_kurtosis',
'd_h3_text_kurtosis_trimmed',
'd_h3_text_mean',
'd_h3_text_mean_trimmed',
'd_h3_text_median',
'd_h3_text_median_abs_dev',
'd_h3_text_rel_std_dev',
'd_h3_text_skewness',
'd_h3_text_skewness_trimmed',
'd_h3_text_std_dev',
'd_h3_text_std_dev_trimmed',
'd_h3_text_variance',
'd_h4_header_count',
'd_h4_header_kurtosis',
'd_h4_header_kurtosis_trimmed',
'd_h4_header_mean',
'd_h4_header_mean_trimmed',
'd_h4_header_median',
'd_h4_header_median_abs_dev',
'd_h4_header_rel_std_dev',
'd_h4_header_skewness',
'd_h4_header_skewness_trimmed',
'd_h4_header_std_dev',
'd_h4_header_std_dev_trimmed',
'd_h4_header_variance',
'd_h4_text_count',
'd_h4_text_kurtosis',
'd_h4_text_kurtosis_trimmed',
'd_h4_text_mean',
'd_h4_text_mean_trimmed',
'd_h4_text_median',
'd_h4_text_median_abs_dev',
'd_h4_text_rel_std_dev',
'd_h4_text_skewness',
'd_h4_text_skewness_trimmed',
'd_h4_text_std_dev',
'd_h4_text_std_dev_trimmed',
'd_h4_text_variance',
'd_h5_header_count',
'd_h5_header_kurtosis',
'd_h5_header_kurtosis_trimmed',
'd_h5_header_mean',
'd_h5_header_mean_trimmed',
'd_h5_header_median',
'd_h5_header_median_abs_dev',
'd_h5_header_rel_std_dev',
'd_h5_header_skewness',
'd_h5_header_skewness_trimmed',
'd_h5_header_std_dev',
'd_h5_header_std_dev_trimmed',
'd_h5_header_variance',
'd_h5_text_count',
'd_h5_text_kurtosis',
'd_h5_text_kurtosis_trimmed',
'd_h5_text_mean',
'd_h5_text_mean_trimmed',
'd_h5_text_median',
'd_h5_text_median_abs_dev',
'd_h5_text_rel_std_dev',
'd_h5_text_skewness',
'd_h5_text_skewness_trimmed',
'd_h5_text_std_dev',
'd_h5_text_std_dev_trimmed',
'd_h5_text_variance',
'd_has_ext_link_sect',
'd_has_notes_sect',
'd_has_ref_sect',
'd_infobox_count',
]
link_attrs = ['bl_count',
'd_cat_count',
'd_dead_link_count',
'd_ext_link_count',
'd_ext_link_per_w',
'd_ext_link_sect_li_count',
'd_hidden_cat_count',
'd_hn_dablink_count',
'd_hn_mainlink_count',
'd_hn_relarticle_count',
'd_hn_rellink_count',
'd_hn_seealso_count',
'd_int_link_text_count',
'd_int_link_text_kurtosis',
'd_int_link_text_kurtosis_trimmed',
'd_int_link_text_mean',
'd_int_link_text_mean_trimmed',
'd_int_link_text_median',
'd_int_link_text_median_abs_dev',
'd_int_link_text_rel_std_dev',
'd_int_link_text_skewness',
'd_int_link_text_skewness_trimmed',
'd_int_link_text_std_dev',
'd_int_link_text_std_dev_trimmed',
'd_int_link_text_variance',
'd_metadata_link_count',
'd_navbox_word_count',
'd_navbox_word_kurtosis',
'd_navbox_word_kurtosis_trimmed',
'd_navbox_word_mean',
'd_navbox_word_mean_trimmed',
'd_navbox_word_median',
'd_navbox_word_median_abs_dev',
'd_navbox_word_rel_std_dev',
'd_navbox_word_skewness',
'd_navbox_word_skewness_trimmed',
'd_navbox_word_std_dev',
'd_navbox_word_std_dev_trimmed',
'd_navbox_word_variance',
'd_see_also_sect_li_count',
'iw_count',
'll_count',
]
last_90_revs_attrs = ['pv_90_days_count',
'pv_90_days_kurtosis',
'pv_90_days_kurtosis_trimmed',
'pv_90_days_mean',
'pv_90_days_mean_trimmed',
'pv_90_days_median',
'pv_90_days_median_abs_dev',
'pv_90_days_rel_std_dev',
'pv_90_days_skewness',
'pv_90_days_skewness_trimmed',
'pv_90_days_std_dev',
'pv_90_days_std_dev_trimmed',
'pv_90_days_variance',
'rv_all_90_days_abs_byte_count',
'rv_all_90_days_abs_byte_kurtosis',
'rv_all_90_days_abs_byte_kurtosis_trimmed',
'rv_all_90_days_abs_byte_mean',
'rv_all_90_days_abs_byte_mean_trimmed',
'rv_all_90_days_abs_byte_median',
'rv_all_90_days_abs_byte_median_abs_dev',
'rv_all_90_days_abs_byte_rel_std_dev',
'rv_all_90_days_abs_byte_skewness',
'rv_all_90_days_abs_byte_skewness_trimmed',
'rv_all_90_days_abs_byte_std_dev',
'rv_all_90_days_abs_byte_std_dev_trimmed',
'rv_all_90_days_abs_byte_variance',
'rv_all_90_days_blank_count',
'rv_all_90_days_by_day_count',
'rv_all_90_days_by_day_kurtosis',
'rv_all_90_days_by_day_kurtosis_trimmed',
'rv_all_90_days_by_day_mean',
'rv_all_90_days_by_day_mean_trimmed',
'rv_all_90_days_by_day_median',
'rv_all_90_days_by_day_median_abs_dev',
'rv_all_90_days_by_day_rel_std_dev',
'rv_all_90_days_by_day_skewness',
'rv_all_90_days_by_day_skewness_trimmed',
'rv_all_90_days_by_day_std_dev',
'rv_all_90_days_by_day_std_dev_trimmed',
'rv_all_90_days_by_day_variance',
'rv_all_90_days_byte_count',
'rv_all_90_days_count',
'rv_all_90_days_deleted_count',
'rv_all_90_days_ed_returning',
'rv_all_90_days_ed_top_20',
'rv_all_90_days_ed_top_20_bytes',
'rv_all_90_days_ed_top_5',
'rv_all_90_days_ed_top_5_bytes',
'rv_all_90_days_ed_unique',
'rv_all_90_days_est_revert_count',
'rv_all_90_days_ip_edit_count',
'rv_all_90_days_minor_count',
'rv_wo_undid_90_days_abs_byte_count',
'rv_wo_undid_90_days_abs_byte_kurtosis',
'rv_wo_undid_90_days_abs_byte_kurtosis_trimmed',
'rv_wo_undid_90_days_abs_byte_mean',
'rv_wo_undid_90_days_abs_byte_mean_trimmed',
'rv_wo_undid_90_days_abs_byte_median',
'rv_wo_undid_90_days_abs_byte_median_abs_dev',
'rv_wo_undid_90_days_abs_byte_rel_std_dev',
'rv_wo_undid_90_days_abs_byte_skewness',
'rv_wo_undid_90_days_abs_byte_skewness_trimmed',
'rv_wo_undid_90_days_abs_byte_std_dev',
'rv_wo_undid_90_days_abs_byte_std_dev_trimmed',
'rv_wo_undid_90_days_abs_byte_variance',
'rv_wo_undid_90_days_blank_count',
'rv_wo_undid_90_days_by_day_count',
'rv_wo_undid_90_days_by_day_kurtosis',
'rv_wo_undid_90_days_by_day_kurtosis_trimmed',
'rv_wo_undid_90_days_by_day_mean',
'rv_wo_undid_90_days_by_day_mean_trimmed',
'rv_wo_undid_90_days_by_day_median',
'rv_wo_undid_90_days_by_day_median_abs_dev',
'rv_wo_undid_90_days_by_day_rel_std_dev',
'rv_wo_undid_90_days_by_day_skewness',
'rv_wo_undid_90_days_by_day_skewness_trimmed',
'rv_wo_undid_90_days_by_day_std_dev',
'rv_wo_undid_90_days_by_day_std_dev_trimmed',
'rv_wo_undid_90_days_by_day_variance',
'rv_wo_undid_90_days_byte_count',
'rv_wo_undid_90_days_count',
'rv_wo_undid_90_days_deleted_count',
'rv_wo_undid_90_days_ed_returning',
'rv_wo_undid_90_days_ed_top_20',
'rv_wo_undid_90_days_ed_top_20_bytes',
'rv_wo_undid_90_days_ed_top_5',
'rv_wo_undid_90_days_ed_top_5_bytes',
'rv_wo_undid_90_days_ed_unique',
'rv_wo_undid_90_days_est_revert_count',
'rv_wo_undid_90_days_ip_edit_count',
'rv_wo_undid_90_days_minor_count',
'rv_t_all_90_days_abs_byte_count',
'rv_t_all_90_days_abs_byte_kurtosis',
'rv_t_all_90_days_abs_byte_kurtosis_trimmed',
'rv_t_all_90_days_abs_byte_mean',
'rv_t_all_90_days_abs_byte_mean_trimmed',
'rv_t_all_90_days_abs_byte_median',
'rv_t_all_90_days_abs_byte_median_abs_dev',
'rv_t_all_90_days_abs_byte_rel_std_dev',
'rv_t_all_90_days_abs_byte_skewness',
'rv_t_all_90_days_abs_byte_skewness_trimmed',
'rv_t_all_90_days_abs_byte_std_dev',
'rv_t_all_90_days_abs_byte_std_dev_trimmed',
'rv_t_all_90_days_abs_byte_variance',
'rv_t_all_90_days_blank_count',
'rv_t_all_90_days_by_day_count',
'rv_t_all_90_days_by_day_kurtosis',
'rv_t_all_90_days_by_day_kurtosis_trimmed',
'rv_t_all_90_days_by_day_mean',
'rv_t_all_90_days_by_day_mean_trimmed',
'rv_t_all_90_days_by_day_median',
'rv_t_all_90_days_by_day_median_abs_dev',
'rv_t_all_90_days_by_day_rel_std_dev',
'rv_t_all_90_days_by_day_skewness',
'rv_t_all_90_days_by_day_skewness_trimmed',
'rv_t_all_90_days_by_day_std_dev',
'rv_t_all_90_days_by_day_std_dev_trimmed',
'rv_t_all_90_days_by_day_variance',
'rv_t_all_90_days_byte_count',
'rv_t_all_90_days_count',
'rv_t_all_90_days_deleted_count',
'rv_t_all_90_days_ed_returning',
'rv_t_all_90_days_ed_top_20',
'rv_t_all_90_days_ed_top_20_bytes',
'rv_t_all_90_days_ed_top_5',
'rv_t_all_90_days_ed_top_5_bytes',
'rv_t_all_90_days_ed_unique',
'rv_t_all_90_days_est_revert_count',
'rv_t_all_90_days_ip_edit_count',
'rv_t_all_90_days_minor_count',
'gn_count',
'gs_count',
'wa_count']
freq_rev_attrs = ['rv_all_all_by_day_count',
'rv_all_all_by_day_kurtosis',
'rv_all_all_by_day_kurtosis_trimmed',
'rv_all_all_by_day_mean',
'rv_all_all_by_day_mean_trimmed',
'rv_all_all_by_day_median',
'rv_all_all_by_day_median_abs_dev',
'rv_all_all_by_day_rel_std_dev',
'rv_all_all_by_day_skewness',
'rv_all_all_by_day_skewness_trimmed',
'rv_all_all_by_day_std_dev',
'rv_all_all_by_day_std_dev_trimmed',
'rv_all_all_by_day_variance',
'rv_all_first_age',
'rv_all_latest_age',
'rv_wo_undid_all_by_day_count',
'rv_wo_undid_all_by_day_kurtosis',
'rv_wo_undid_all_by_day_kurtosis_trimmed',
'rv_wo_undid_all_by_day_mean',
'rv_wo_undid_all_by_day_mean_trimmed',
'rv_wo_undid_all_by_day_median',
'rv_wo_undid_all_by_day_median_abs_dev',
'rv_wo_undid_all_by_day_rel_std_dev',
'rv_wo_undid_all_by_day_skewness',
'rv_wo_undid_all_by_day_skewness_trimmed',
'rv_wo_undid_all_by_day_std_dev',
'rv_wo_undid_all_by_day_std_dev_trimmed',
'rv_wo_undid_all_by_day_variance',
'rv_wo_undid_first_age',
'rv_wo_undid_latest_age',
'rv_t_all_all_by_day_count',
'rv_t_all_all_by_day_kurtosis',
'rv_t_all_all_by_day_kurtosis_trimmed',
'rv_t_all_all_by_day_mean',
'rv_t_all_all_by_day_mean_trimmed',
'rv_t_all_all_by_day_median',
'rv_t_all_all_by_day_median_abs_dev',
'rv_t_all_all_by_day_rel_std_dev',
'rv_t_all_all_by_day_skewness',
'rv_t_all_all_by_day_skewness_trimmed',
'rv_t_all_all_by_day_std_dev',
'rv_t_all_all_by_day_std_dev_trimmed',
'rv_t_all_all_by_day_variance',
'rv_t_all_first_age',
'rv_t_all_latest_age',
'rv_all_interval_count',
'rv_all_interval_kurtosis',
'rv_all_interval_kurtosis_trimmed',
'rv_all_interval_mean',
'rv_all_interval_mean_trimmed',
'rv_all_interval_median',
'rv_all_interval_median_abs_dev',
'rv_all_interval_rel_std_dev',
'rv_all_interval_skewness',
'rv_all_interval_skewness_trimmed',
'rv_all_interval_std_dev',
'rv_all_interval_std_dev_trimmed',
'rv_all_interval_variance',
'rv_t_all_interval_count',
'rv_t_all_interval_kurtosis',
'rv_t_all_interval_kurtosis_trimmed',
'rv_t_all_interval_mean',
'rv_t_all_interval_mean_trimmed',
'rv_t_all_interval_median',
'rv_t_all_interval_median_abs_dev',
'rv_t_all_interval_rel_std_dev',
'rv_t_all_interval_skewness',
'rv_t_all_interval_skewness_trimmed',
'rv_t_all_interval_std_dev',
'rv_t_all_interval_std_dev_trimmed',
'rv_t_all_interval_variance', ]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment