These are chat archives for FreeCodeCamp/DataScience
discussion on how we can use statistical methods to measure and improve the efficacy of http://freeCodeCamp.com
for review in reviews: for word in review.split(' '): if total_counts[word] > min_count: if word in pos_neg_ratios.keys(): if pos_neg_ratios[word] >= polarity_cutoff or pos_neg_ratios[word] <= -polarity_cutoff: review_vocab.add(word) else: review_vocab.add(word)
evaristoc sends brownie points to @becausealice2 :sparkles: :thumbsup: :sparkles:
review_vocabis a set so it should contain only 1 word without duplicates.
elsecondition. Not sure what you are trying to do with adding those words.
review_vocab—I think a word would only be added to the
review_vocabif its number of occurrences in
reviewis less than
min_count. Guessing without context, I think a word would only be added to
review_vocabthrough the conditions after the first
ifif its frequency of appearance (or perhaps distribution) in
reviewis outside of the expected range (
I got really distracted when I was about to start the D3 force-directed graph project and ended up doing this: http://codepen.io/honmanyau/full/NjwQbq
Would this be along the line of something useful? :) If so, and if the derived dataset seems useful, I was wondering if someone could babysit me through how to go about sharing it on GitHub once!
if. I swear it was the first, though...
elsecondition is not required then.
The data for this force-directed graph is derived from the 2017 New Coder Survey conducted by Free Code Camp (GitHub repository). This particular derived dataset shows in which other communities 13803 Campers are also involved in.
Sorry! I was opening the editor in a small window! It is GREAT! @honmanyau
## New for Project 6: only add words that occur at least min_count times # and for words with pos/neg ratios, only add words # that meet the polarity_cutoff
Change so words are only added to the vocabulary if they occur in the vocabulary more than min_count times. Change so words are only added to the vocabulary if the absolute value of their postive-to-negative ratio is at least polarity_cutoff
For those interested in visualizations using Python:
at leastmeans equal or more, so "more than" is incorrect
polarity_cutoffseems to be a concept; I think this is correct
iffilters for all
min_countwords BUT for those that are
pos/neg ratios, just only those that meet
About getting a degree as Data Scientist. This is a discussion. I think having an scientific way of thinking is required and that gets trained at uni, not always in MOOCs. Also the theoretical background could be required.
My question mark about studying data science without a good uni background could suggest that only knowing the methods is enough. What it is not told by many of those courses is when your results are misled. Critical thinking is not learned in MOOCs, IMO. You need a bit more than that.
(Sorry, checking my twitter that I let abandoned...)
jayvora92 sends brownie points to @evaristoc and @erictleung :sparkles: :thumbsup: :sparkles:
nmbrgts sends brownie points to @evaristoc :sparkles: :thumbsup: :sparkles: