Really close to having it all now

This commit is contained in:
benjamin melançon 2021-04-27 23:37:37 -04:00
parent 1c63ab32e8
commit 4314ad0774

View file

@ -4,6 +4,15 @@ import numpy as np
timelog = pd.read_csv("timelog-titled.csv") timelog = pd.read_csv("timelog-titled.csv")
# Dump bad data. The real solution here is to get rid of the damned 'Cancel'
# button on the Pomodoro Prompt dialog, but i don't know how to do that, so we
# need to drop the rows where the work task description is blank, which is
# coming in as not a number for reasons i'm not entirely clear on. Maybe
# because it's the last row of the spreadsheet? Anyway we cannot do anything
# with no data in the description, so drop them at the outset.
timelog = timelog.dropna()
timelog = timelog.reset_index(drop=True)
timelog["started"] = pd.to_datetime(timelog["started"]).dt.tz_convert("US/Eastern") timelog["started"] = pd.to_datetime(timelog["started"]).dt.tz_convert("US/Eastern")
timelog["recorded"] = pd.to_datetime(timelog["recorded"]).dt.tz_convert("US/Eastern") timelog["recorded"] = pd.to_datetime(timelog["recorded"]).dt.tz_convert("US/Eastern")
timelog["time"] = 30 timelog["time"] = 30
@ -13,6 +22,9 @@ timelog["time"] = 30
timelog["date"] = timelog["started"].dt.tz_convert("US/Pacific").dt.date timelog["date"] = timelog["started"].dt.tz_convert("US/Pacific").dt.date
timelog["day_of_week"] = pd.to_datetime(timelog["date"]).dt.day_name() timelog["day_of_week"] = pd.to_datetime(timelog["date"]).dt.day_name()
# For debugging, keep original description around.
timelog["orig_desc"] = timelog["description"]
# Clean up description before we go to work on it. # Clean up description before we go to work on it.
timelog['description'] = timelog['description'].str.strip() timelog['description'] = timelog['description'].str.strip()
@ -26,10 +38,14 @@ timelog['description'] = timelog['description'].str.strip()
# If a multiplier has been provided (an asterisk and an integer at the end of a # If a multiplier has been provided (an asterisk and an integer at the end of a
# task), then multiply the time by it and remove it from the description. # task), then multiply the time by it and remove it from the description.
timelog['tmp_multiplier'] = (np.where(timelog['description'].str.contains('\*\s*\d\s*$'), timelog['description'].str.rsplit('*', 1).str[1].str.strip(), None)) # Ensure we're splitting on the same asterisk we found: Use the end of string
timelog['description'] = (np.where(timelog['description'].str.contains(pat='', regex=False), timelog['description'].str.split('*', 1).str[0], timelog['description'])) # signifier in the regular expression ($), and split from the right.
timelog['tmp_multiplier'] = (np.where(timelog['description'].str.contains('\*\s*\d$'), timelog['description'].str.rsplit('*', 1).str[1].str.strip(), 1))
timelog['description'] = (np.where(timelog['description'].str.contains('\*\s*\d$'), timelog['description'].str.rsplit('*', 1).str[0], timelog['description']))
timelog["time"] = timelog["time"] * timelog['tmp_multiplier'].astype(int)
timelog['tmp_multiplier'].drop()
# Clean up description again, after its been sliced and diced. # Clean up description again, after it has been sliced and diced.
timelog['description'] = timelog['description'].str.strip() timelog['description'] = timelog['description'].str.strip()
# Condense duplicate entries by date, summing the minutes spent, and listing # Condense duplicate entries by date, summing the minutes spent, and listing