From b86269bbe2483b49f528498c860e9a5b198f849c Mon Sep 17 00:00:00 2001
From: Paul Arterburn <paularterburn@gmail.com>
Date: Fri, 13 Dec 2024 20:07:29 -0700
Subject: [PATCH] stats tweaks

---
 app/models/entry.rb  |  2 +-
 lib/tasks/entry.rake | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/app/models/entry.rb b/app/models/entry.rb
index 2055b151..6b2de39c 100644
--- a/app/models/entry.rb
+++ b/app/models/entry.rb
@@ -7,7 +7,7 @@ class Entry < ActiveRecord::Base
   mount_uploader :image, ImageUploader
 
   WORDS_NOT_TO_COUNT = ['s', 'amp', '-', 'p', 'br', 'div', 'img', 'span', 'hr', '<', '>']
-  COMMON_WORDS = WORDS_NOT_TO_COUNT + ['your', 'we', 'i', "it's", 'dabblemegpt', 'like', 'these', 'you', 'so', 'went', 'while', 's', 'amp', '-', 'p', 'br', 'div', 'img', 'span', 'the', 'of', 'and', 'a', 'to', 'in', 'is', 'that', 'it', 'was', 'for', 'on', 'are', 'as', 'with', 'at', 'be', 'this', 'have', 'from', 'or', 'had', 'by', 'but', 'not', 'what', 'all', 'were', 'when', 'can', 'said', 'there', 'use', 'an', 'each', 'which', 'do', 'how', 'if']
+  COMMON_WORDS = WORDS_NOT_TO_COUNT + ['has', 'did', "you're", 'your', 'we', 'i', "it's", 'dabblemegpt', 'like', 'these', 'you', 'so', 'went', 'while', 's', 'amp', '-', 'p', 'br', 'div', 'img', 'span', 'the', 'of', 'and', 'a', 'to', 'in', 'is', 'that', 'it', 'was', 'for', 'on', 'are', 'as', 'with', 'at', 'be', 'this', 'have', 'from', 'or', 'had', 'by', 'but', 'not', 'what', 'all', 'were', 'when', 'can', 'said', 'there', 'use', 'an', 'each', 'which', 'do', 'how', 'if']
 
   belongs_to :user
   belongs_to :inspiration, optional: true
diff --git a/lib/tasks/entry.rake b/lib/tasks/entry.rake
index 2a50b859..669bb1f8 100644
--- a/lib/tasks/entry.rake
+++ b/lib/tasks/entry.rake
@@ -162,18 +162,18 @@ namespace :entry do
     # p "Total characters: #{number_with_delimiter(total_chars)}"
     # p "Avg characters per post: #{number_with_delimiter(avg_chars)} (#{avg_tweets_per_post} tweets)"
 
-    counter = WordsCounted.count(entries_bodies)
-    most_frequent = counter.token_frequency.first(400).select { |w| !Entry::COMMON_WORDS.include?(w[0]) }.first(40).map { |w| "#{w[0]}: #{number_with_delimiter(w[1])}" }
-    p "Most Frequent Words:"
-    puts most_frequent
-    p "*"*100
+    # counter = WordsCounted.count(entries_bodies)
+    # most_frequent = counter.token_frequency.first(400).select { |w| !Entry::COMMON_WORDS.include?(w[0]) }.first(40).map { |w| "#{w[0]}: #{number_with_delimiter(w[1])}" }
+    # p "Most Frequent Words:"
+    # puts most_frequent
+    # p "*"*100
   end
 
   # heroku run bundle exec rake "entry:stats_by_user[2022]" --app dabble-me --size=standard-2x
   task :stats_by_user, [:year] => :environment do |_, year:|
     data = []
     csv_data = CSV.generate(col_sep: "\t") do |csv|
-      csv << ["USER_ID", "EMAIL", "#{year}_ENTRY", "#{year}_WORD", "#{year}_TWEET"]
+      csv << ["USER_ID", "EMAIL", "#{year}_ENTRY", "#{year}_WORD"]
 
       User.all.each do |user|
         user_entries = Entry.where("date >= '#{year}-01-01'::DATE AND date <= '#{year}-12-31'::DATE AND user_id = ?", user.id)