Congrats on beginning your adventure with Python! Not everything in this post might make sense right now but bookmark it and comeback to it if it seems helpful later. Eventually you should try to move from scripting to software engineering, and here are a few ideas for you!
With great power comes great responsibility, and as a Python developer you need to be more disciplined than other languages which don't hold your hand and enforce "good" design.
I find it helps to start with a top-down design.
def main():
text = get_text()
p_text = process_text(text)
catalogue = process_catalogue(p_text)
BOOM! You just wrote the whole program -- now you just need to back and fill in the blanks! When you do it like this, it seems less intimidating. Personally, I don't consider myself smart enough to solve very big problems, but I'm a pro at solving small problems. So lets tackle one thing at a time. I'm going to start with 'process_text'.
def process_text(text):
b_text = bundle_dialogue_items(text)
f_text = filter_dialogue_items(b_text)
c_text = clean_dialogue_items(f_text)
I'm not really sure what those things mean yet, but I know that text problems tend to follow a pattern called "map/reduce" which means you perform and operation on something and then you clean it up and combine, so I put in some placeholder functions. I might go back and add more if necessary.
Now let's write 'process_catalogue'. I could've written "process_dict" but that sounded lame to me.
def process_catalogue(p_text):
speakers = make_catalogue(c_text)
s_speakers = sum_words_per_paragraph_items(speakers)
t_speakers = total_word_count(s_speakers)
Cool. Not too bad. You might approach this different than me, but I thought it would make sense to aggregate the items, the count the words per paragraph, and then count all the words.
So, at this point I'd probably make one or two little 'lib' (library) modules to back-fill the remaining functions. For the sake you being able to run this without worrying about imports, I'm going to stick it all in one .py file, but eventually you'll learn how to break these up so it looks nicer. So let's do this.
# ------------------ #
# == process_text == #
# ------------------ #
def bundle_dialogue_items(lines):
cur_speaker = None
paragraphs = Counter()
for line in lines:
if re.match(p, line):
cur_speaker, dialogue = line.split(':')
paragraphs[cur_speaker] += 1
else:
dialogue = line
res = cur_speaker, dialogue, paragraphs[cur_speaker]
yield res
def filter_dialogue_items(lines):
for name, dialogue, paragraph in lines:
if dialogue:
res = name, dialogue, paragraph
yield res
def clean_dialogue_items(flines):
for name, dialogue, paragraph in flines:
s_dialogue = dialogue.strip().split()
c_dialouge = [clean_word(w) for w in s_dialogue]
res = name, c_dialouge, paragraph
yield res
aaaand a little helper function
# ------------------- #
# == aux functions == #
# ------------------- #
to_clean = string.whitespace + string.punctuation
def clean_word(word):
res = ''.join(c for c in word if c not in to_clean)
return res
So it may not be obvious but this library is designed as a data processing pipeline. There several ways to process data, one is pipeline processing and another is batch processing. Let's take a look at batch processing.
# ----------------------- #
# == process_catalogue == #
# ----------------------- #
speaker_stats = 'stats'
def make_catalogue(names_with_dialogue):
speakers = {}
for name, dialogue, paragraph in names_with_dialogue:
speaker = speakers.setdefault(name, {})
stats = speaker.setdefault(speaker_stats, {})
stats.setdefault(paragraph, []).extend(dialogue)
return speakers
word_count = 'word_count'
def sum_words_per_paragraph_items(speakers):
for speaker in speakers:
word_stats = speakers[speaker][speaker_stats]
speakers[speaker][word_count] = Counter()
for paragraph in word_stats:
speakers[speaker][word_count][paragraph] += len(word_stats[paragraph])
return speakers
total = 'total'
def total_word_count(speakers):
for speaker in speakers:
wc = speakers[speaker][word_count]
speakers[speaker][total] = 0
for c in wc:
speakers[speaker][total] += wc[c]
return speakers
All these nested dictionaries are getting a little complicated. In actual production code I would replace these with some more readable classes (along with adding tests and docstrings!!), but I don't want to make this more confusing than it already is! Alright, for your convenience below is the whole thing put together.
import pprint
import re
import string
from collections import Counter
p = re.compile(r'(\w+?):')
def get_text_line_items(text):
for line in text.split('\n'):
yield line
def bundle_dialogue_items(lines):
cur_speaker = None
paragraphs = Counter()
for line in lines:
if re.match(p, line):
cur_speaker, dialogue = line.split(':')
paragraphs[cur_speaker] += 1
else:
dialogue = line
res = cur_speaker, dialogue, paragraphs[cur_speaker]
yield res
def filter_dialogue_items(lines):
for name, dialogue, paragraph in lines:
if dialogue:
res = name, dialogue, paragraph
yield res
to_clean = string.whitespace + string.punctuation
def clean_word(word):
res = ''.join(c for c in word if c not in to_clean)
return res
def clean_dialogue_items(flines):
for name, dialogue, paragraph in flines:
s_dialogue = dialogue.strip().split()
c_dialouge = [clean_word(w) for w in s_dialogue]
res = name, c_dialouge, paragraph
yield res
speaker_stats = 'stats'
def make_catalogue(names_with_dialogue):
speakers = {}
for name, dialogue, paragraph in names_with_dialogue:
speaker = speakers.setdefault(name, {})
stats = speaker.setdefault(speaker_stats, {})
stats.setdefault(paragraph, []).extend(dialogue)
return speakers
def clean_dict(speakers):
for speaker in speakers:
stats = speakers[speaker][speaker_stats]
for paragraph in stats:
stats[paragraph] = [''.join(c for c in word if c not in to_clean)
for word in stats[paragraph]]
return speakers
word_count = 'word_count'
def sum_words_per_paragraph_items(speakers):
for speaker in speakers:
word_stats = speakers[speaker][speaker_stats]
speakers[speaker][word_count] = Counter()
for paragraph in word_stats:
speakers[speaker][word_count][paragraph] += len(word_stats[paragraph])
return speakers
total = 'total'
def total_word_count(speakers):
for speaker in speakers:
wc = speakers[speaker][word_count]
speakers[speaker][total] = 0
for c in wc:
speakers[speaker][total] += wc[c]
return speakers
def get_text():
text = '''BOB: blah blah blah blah
blah hello goodbye etc.
JERRY:.............................................
...............
BOB:blah blah blah
blah blah blah
blah.
BOB: boopy doopy doop
P1: Bla bla bla.
P2: Bla bla bla bla.
P1: Bla bla.
P3: Bla.'''
text = get_text_line_items(text)
return text
def process_catalogue(c_text):
speakers = make_catalogue(c_text)
s_speakers = sum_words_per_paragraph_items(speakers)
t_speakers = total_word_count(s_speakers)
return t_speakers
def process_text(text):
b_text = bundle_dialogue_items(text)
f_text = filter_dialogue_items(b_text)
c_text = clean_dialogue_items(f_text)
return c_text
def main():
text = get_text()
c_text = process_text(text)
t_speakers = process_catalogue(c_text)
# take a look at your hard work!
pprint.pprint(t_speakers)
if __name__ == '__main__':
main()
So this script is almost certainly overkill for this application, but the point is to see what (questionably) readable, maintainable, modular Python code might look like.
Pretty sure output looks something like:
{'BOB': {'stats': {1: ['blah',
'blah',
'blah',
'blah',
'blah',
'hello',
'goodbye',
'etc'],
2: ['blah',
'blah',
'blah',
'blah',
'blah',
'blah',
'blah'],
3: ['boopy', 'doopy', 'doop']},
'total': 18,
'word_count': Counter({1: 8, 2: 7, 3: 3})},
'JERRY': {'stats': {1: ['', '']}, 'total': 2, 'word_count': Counter({1: 2})},
'P1': {'stats': {1: ['Bla', 'bla', 'bla'], 2: ['Bla', 'bla']},
'total': 5,
'word_count': Counter({1: 3, 2: 2})},
'P2': {'stats': {1: ['Bla', 'bla', 'bla', 'bla']},
'total': 4,
'word_count': Counter({1: 4})},
'P3': {'stats': {1: ['Bla']}, 'total': 1, 'word_count': Counter({1: 1})}}
