Master thesis: genre abandonment

collection of the scripts used to collect, process and analyze the data due to frequent re-writing, not all files are used, of most importance are

MLHD processing

• ch_setups.py: defining CH tables; not intended for wholesale execution
• mlhd_dl.py: downloading MLHD data using selenium
• read_in_ch_blk.py: enters logs of specific directories into CH; optimized version of read_in_clickhouse.py

data collection

• tags_splt1.py: query musicbrainz: requires list of mbids
• tags22.py: query last.fm id, relies on tags_splt1 output
• acst_brainz.py: downloads AcousticBrainz data
• addgs.py: processing API data; not intended for wholesale execution

data processing

• gnrl_funcs.py: mostly used to construct data frame
• acst_hier.py: workhorse for processing time chunks
• aux_funcs: functions for visualizing, plotting graphs
• acst_hier_mnng.py: running different thresholds for acst_hier.py

data analyzing

• swivl.R: developing general framework of survival models; not used for final analysis
• robust: actual analysis, generates tables
• figures.py: produces figures, relies on acst_hier.py data objects