diff --git "a/bitcoinforum/1_forum_dataset/visualize_data.ipynb" "b/bitcoinforum/1_forum_dataset/visualize_data.ipynb" new file mode 100644--- /dev/null +++ "b/bitcoinforum/1_forum_dataset/visualize_data.ipynb" @@ -0,0 +1,1433 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import os\n", + "import gzip\n", + "import pickle\n", + "\n", + "# category = \"groupbuys\"\n", + "category = \"hardware\"\n", + "# category = \"miners\"\n", + "# category = \"mining\"\n", + "# category = \"mining_support\"\n", + "# category = \"pools\"\n", + "\n", + "# category = \"mining_speculation\"\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "total posts in the category groupbuys : 80095\n", + "total posts in the category hardware : 349144\n", + "total posts in the category miners : 60831\n", + "total posts in the category mining : 39236\n", + "total posts in the category mining_support : 58811\n", + "total threads: 24189\n", + "total characters: 194938984\n", + "total posts: 588117\n" + ] + } + ], + "source": [ + "categories = [\n", + " \"groupbuys\",\n", + " \"hardware\",\n", + " \"miners\",\n", + " \"mining\",\n", + " \"mining_support\",\n", + " # \"pools\",\n", + " # \"mining_speculation\"\n", + "]\n", + "\n", + "total_threads = 0\n", + "total_chars = 0\n", + "total_posts_global = 0\n", + "all_dates = []\n", + "\n", + "threads_in_category = []\n", + "\n", + "character_counts = []\n", + "thread_character_counts = []\n", + "for cat in categories:\n", + " with gzip.open('cleaned-data/'+cat+'.pkl.gz', 'rb') as f:\n", + " df_ = pickle.load(f)\n", + " # print(cat, \"number of threads: \", len(df))\n", + " # print(cat, \"average characters per threads: \", df['post'].str.len().mean())\n", + " # print(cat, \"median characters per threads: \", df['post'].str.len().median())\n", + " # print(cat, \"max characters in a thread: \", df['post'].str.len().max())\n", + " # print(cat, \"total characters in the category \", cat, \": \", df_['post'].str.len().sum())\n", + " \n", + " # total_threads += len(df_)\n", + " # total_chars += df_['post'].str.len().sum()\n", + "\n", + " l = len(df_)\n", + " threads_in_category.append({\"category\": cat, \"threads\": l})\n", + " total_threads += l\n", + " total_posts = 0\n", + " thread_character_count = 0\n", + " for (id,row) in df_.iterrows():\n", + " lp = 0\n", + " for post in row[\"post\"].split(\"\"):\n", + " lp = len(post)\n", + " total_chars += lp\n", + " total_posts += 1\n", + " thread_character_count += lp\n", + "\n", + " for date in row[\"dates\"].split(\"\"):\n", + " all_dates.append(date[:7])\n", + " character_counts.append({\"date\": date[:7], \"chars\": lp})\n", + " break\n", + " thread_character_counts.append(thread_character_count)\n", + "\n", + " # print(cat, \"average characters per post in the thread: \" , total_chars/total_posts)\n", + " print(\"total posts in the category\", cat, \":\", total_posts)\n", + " total_posts_global += total_posts\n", + " \n", + "\n", + "\n", + "print(\"total threads: \", total_threads)\n", + "print(\"total characters: \", total_chars)\n", + "print(\"total posts: \", total_posts_global)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "daily variance and std in character counts: \n", + "chars 113031.248506\n", + "dtype: float64\n", + "chars 336.201202\n", + "dtype: float64\n" + ] + } + ], + "source": [ + "# character_counts looks like this:\n", + "# [{'date': '2013-03', 'chars': 70},\n", + "# {'date': '2013-03', 'chars': 15},\n", + "\n", + "average_chars_per_day = pd.DataFrame(character_counts).groupby(\"date\").mean()\n", + "print(\"daily variance and std in character counts: \")\n", + "print(average_chars_per_day.var())\n", + "print(average_chars_per_day.std())" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 198, 239, 1589, ..., 33828279, 33853133, 33855788])" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# make a bar plot of post length\n", + "# char_counts = pd.DataFrame(character_counts)[\"chars\"].sort_values()\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np\n", + "thread_character_counts = np.array(thread_character_counts)\n", + "thread_character_counts" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "24189" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(thread_character_counts)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "truncated = thread_character_counts[thread_character_counts < 5000]" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "12" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(truncated)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "# plt.hist(truncated, bins=15)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [], + "source": [ + "# with gzip.open('cleaned-data/'+category+'.pkl.gz', 'rb') as f:\n", + "# df = pickle.load(f)\n", + "\n", + "# #print a sample\n", + "# for (id,row) in df.tail(50).iterrows():\n", + "# if(len(row[\"post\"]) < 100):\n", + "# continue\n", + "# print(\"id:\", id)\n", + "# print(\"topic:\", row[\"topic\"])\n", + "# print(\"posts:\")\n", + "# for (post, date) in zip(row[\"post\"].split(\"\"), row[\"dates\"].split(\"\")):\n", + "# # print(\"date:\", date[:10])\n", + "# print(\"date:\", date)\n", + "# if (post.count(\"[\") > 3) and len(post) > 1000:\n", + "# print(\"\")\n", + "# print(post)\n", + "# else:\n", + "# print(post)\n", + "# print(\"---\")\n", + "# print(\"\\n\\n\\n\\n\\n\")" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['2010-09',\n", + " '2010-10',\n", + " '2010-11',\n", + " '2010-11',\n", + " '2010-12',\n", + " '2010-12',\n", + " '2010-12',\n", + " '2011-01',\n", + " '2011-01',\n", + " '2011-01',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-02',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-03',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-04',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-05',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-06',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " '2011-07',\n", + " ...]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#sort all_dates\n", + "all_dates.sort()\n", + "all_dates" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# df[\"month\"] = df[\"dates\"].apply(lambda x: x.split(\"\")[0][:7])\n", + "# #plot distribution of months in threads\n", + "# df[\"month\"].value_counts().sort_index().plot(kind=\"bar\", figsize=(20,10))\n", + "\n", + "import matplotlib.pyplot as plt\n", + "# plot all_dates with a bar plot\n", + "plt.figure(figsize=(20,10))\n", + "value_counts = pd.Series(all_dates).value_counts().sort_index()\n", + "value_counts.plot(kind=\"bar\")" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# obtain a yearly average of value_counts\n", + "yearly = value_counts.groupby(value_counts.index.str[:4]).mean().iloc[1:]\n", + "# yearly.plot(kind=\"bar\")\n", + "# plot with y axis labelled as \"count\", x axis tilted by 30 degrees\n", + "yearly.plot(kind=\"bar\", ylabel=\"Amount of threads\", rot=30)" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# plot threads in category\n", + "plt.figure(figsize=(20,10))\n", + "threads_in_category = pd.DataFrame(threads_in_category)\n", + "threads_in_category.plot(kind=\"bar\", x=\"category\", y=\"threads\")" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "7819\n", + "3173\n" + ] + } + ], + "source": [ + "all_dates = pd.DataFrame(all_dates)\n", + "# count dates after 2014\n", + "print(all_dates[all_dates[0] > \"2015-01\"].value_counts().sum())\n", + "# count dates after 2018\n", + "print(all_dates[all_dates[0] > \"2018-01\"].value_counts().sum())" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "base", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.13" + }, + "orig_nbformat": 4, + "vscode": { + "interpreter": { + "hash": "ad2bdc8ecc057115af97d19610ffacc2b4e99fae6737bb82f5d7fb13d2f2c186" + } + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}