diff --git a/your-code/main.ipynb b/your-code/main.ipynb index bad6d94..4def7d8 100644 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -9,10 +9,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 54, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "import pandas as pd " + ] }, { "cell_type": "markdown", @@ -23,10 +25,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 55, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "user = pd.read_csv(\"users_table.csv\")" + ] }, { "cell_type": "markdown", @@ -37,10 +41,175 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 56, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/html": [ + "
| \n", + " | userId | \n", + "Reputation | \n", + "CreationDate | \n", + "DisplayName | \n", + "LastAccessDate | \n", + "WebsiteUrl | \n", + "Location | \n", + "AboutMe | \n", + "Views | \n", + "UpVotes | \n", + "DownVotes | \n", + "AccountId | \n", + "Age | \n", + "ProfileImageUrl | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "-1 | \n", + "1 | \n", + "2010-07-19 06:55:26 | \n", + "Community | \n", + "2010-07-19 06:55:26 | \n", + "http://meta.stackexchange.com/ | \n", + "on the server farm | \n", + "<p>Hi, I'm not really a person.</p>\\r\\n\\r\\n<p>... | \n", + "0 | \n", + "5007 | \n", + "1920 | \n", + "-1 | \n", + "NaN | \n", + "NaN | \n", + "
| 1 | \n", + "2 | \n", + "101 | \n", + "2010-07-19 14:01:36 | \n", + "Geoff Dalgas | \n", + "2013-11-12 22:07:23 | \n", + "http://stackoverflow.com | \n", + "Corvallis, OR | \n", + "<p>Developer on the StackOverflow team. Find ... | \n", + "25 | \n", + "3 | \n", + "0 | \n", + "2 | \n", + "37.0 | \n", + "NaN | \n", + "
| 2 | \n", + "3 | \n", + "101 | \n", + "2010-07-19 15:34:50 | \n", + "Jarrod Dixon | \n", + "2014-08-08 06:42:58 | \n", + "http://stackoverflow.com | \n", + "New York, NY | \n", + "<p><a href=\"http://blog.stackoverflow.com/2009... | \n", + "22 | \n", + "19 | \n", + "0 | \n", + "3 | \n", + "35.0 | \n", + "NaN | \n", + "
| 3 | \n", + "4 | \n", + "101 | \n", + "2010-07-19 19:03:27 | \n", + "Emmett | \n", + "2014-01-02 09:31:02 | \n", + "http://minesweeperonline.com | \n", + "San Francisco, CA | \n", + "<p>currently at a startup in SF</p>\\r\\n\\r\\n<p>... | \n", + "11 | \n", + "0 | \n", + "0 | \n", + "1998 | \n", + "28.0 | \n", + "http://i.stack.imgur.com/d1oHX.jpg | \n", + "
| 4 | \n", + "5 | \n", + "6792 | \n", + "2010-07-19 19:03:57 | \n", + "Shane | \n", + "2014-08-13 00:23:47 | \n", + "http://www.statalgo.com | \n", + "New York, NY | \n", + "<p>Quantitative researcher focusing on statist... | \n", + "1145 | \n", + "662 | \n", + "5 | \n", + "54503 | \n", + "35.0 | \n", + "NaN | \n", + "
Hi, I'm not really a person.
\\r\\n\\r\\n... 0 5007 \\\n", + "1
Developer on the StackOverflow team. Find ... 25 3 \n", + "2
\\r\\n\\r\\n... 11 0 \n", + "4
Quantitative researcher focusing on statist... 1145 662 \n", + "\n", + " DownVotes AccountId Age ProfileImageUrl \n", + "0 1920 -1 NaN NaN \n", + "1 0 2 37.0 NaN \n", + "2 0 3 35.0 NaN \n", + "3 0 1998 28.0 http://i.stack.imgur.com/d1oHX.jpg \n", + "4 5 54503 35.0 NaN " + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "user.rename(columns = {\"Id\":\"userId\"}, inplace = True)\n", + "user.head()" + ] }, { "cell_type": "markdown", @@ -51,10 +220,114 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 57, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/html": [ + "
| \n", + " | Id | \n", + "PostTypeId | \n", + "AcceptedAnswerId | \n", + "CreaionDate | \n", + "Score | \n", + "ViewCount | \n", + "Body | \n", + "OwnerUserId | \n", + "LasActivityDate | \n", + "Title | \n", + "... | \n", + "AnswerCount | \n", + "CommentCount | \n", + "FavoriteCount | \n", + "LastEditorUserId | \n", + "LastEditDate | \n", + "CommunityOwnedDate | \n", + "ParentId | \n", + "ClosedDate | \n", + "OwnerDisplayName | \n", + "LastEditorDisplayName | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "1 | \n", + "1 | \n", + "15.0 | \n", + "2010-07-19 19:12:12 | \n", + "23 | \n", + "1278.0 | \n", + "<p>How should I elicit prior distributions fro... | \n", + "8.0 | \n", + "2010-09-15 21:08:26 | \n", + "Eliciting priors from experts | \n", + "... | \n", + "5.0 | \n", + "1 | \n", + "14.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
1 rows × 21 columns
\n", + "How should I elicit prior distributions fro... 8.0 \\\n", + "\n", + " LasActivityDate Title ... AnswerCount \n", + "0 2010-09-15 21:08:26 Eliciting priors from experts ... 5.0 \\\n", + "\n", + " CommentCount FavoriteCount LastEditorUserId LastEditDate \n", + "0 1 14.0 NaN NaN \\\n", + "\n", + " CommunityOwnedDate ParentId ClosedDate OwnerDisplayName \n", + "0 NaN NaN NaN NaN \\\n", + "\n", + " LastEditorDisplayName \n", + "0 NaN \n", + "\n", + "[1 rows x 21 columns]" + ] + }, + "execution_count": 57, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "posts = pd.read_csv(\"posts_table.csv\")\n", + "posts.head(1)" + ] }, { "cell_type": "markdown", @@ -65,10 +338,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 58, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "posts.rename(columns = {\"Id\":\"postId\", \"OwnerUserId\": \"userId\"}, inplace = True)" + ] }, { "cell_type": "markdown", @@ -81,10 +356,301 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 59, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/html": [ + "
| \n", + " | userId | \n", + "Reputation | \n", + "Views | \n", + "UpVotes | \n", + "DownVotes | \n", + "
|---|---|---|---|---|---|
| 0 | \n", + "-1 | \n", + "1 | \n", + "0 | \n", + "5007 | \n", + "1920 | \n", + "
| 1 | \n", + "2 | \n", + "101 | \n", + "25 | \n", + "3 | \n", + "0 | \n", + "
| 2 | \n", + "3 | \n", + "101 | \n", + "22 | \n", + "19 | \n", + "0 | \n", + "
| 3 | \n", + "4 | \n", + "101 | \n", + "11 | \n", + "0 | \n", + "0 | \n", + "
| 4 | \n", + "5 | \n", + "6792 | \n", + "1145 | \n", + "662 | \n", + "5 | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
| 40320 | \n", + "55743 | \n", + "1 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "
| 40321 | \n", + "55744 | \n", + "6 | \n", + "1 | \n", + "0 | \n", + "0 | \n", + "
| 40322 | \n", + "55745 | \n", + "101 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "
| 40323 | \n", + "55746 | \n", + "106 | \n", + "1 | \n", + "0 | \n", + "0 | \n", + "
| 40324 | \n", + "55747 | \n", + "1 | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "
40325 rows × 5 columns
\n", + "| \n", + " | postId | \n", + "Score | \n", + "userId | \n", + "ViewCount | \n", + "CommentCount | \n", + "
|---|---|---|---|---|---|
| 0 | \n", + "1 | \n", + "23 | \n", + "8.0 | \n", + "1278.0 | \n", + "1 | \n", + "
| 1 | \n", + "2 | \n", + "22 | \n", + "24.0 | \n", + "8198.0 | \n", + "1 | \n", + "
| 2 | \n", + "3 | \n", + "54 | \n", + "18.0 | \n", + "3613.0 | \n", + "4 | \n", + "
| 3 | \n", + "4 | \n", + "13 | \n", + "23.0 | \n", + "5224.0 | \n", + "2 | \n", + "
| 4 | \n", + "5 | \n", + "81 | \n", + "23.0 | \n", + "NaN | \n", + "3 | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
| 39995 | \n", + "48321 | \n", + "0 | \n", + "19966.0 | \n", + "NaN | \n", + "0 | \n", + "
| 39996 | \n", + "48322 | \n", + "3 | \n", + "892.0 | \n", + "NaN | \n", + "2 | \n", + "
| 39997 | \n", + "48323 | \n", + "1 | \n", + "2020.0 | \n", + "NaN | \n", + "0 | \n", + "
| 39998 | \n", + "48324 | \n", + "3 | \n", + "19914.0 | \n", + "NaN | \n", + "0 | \n", + "
| 39999 | \n", + "48325 | \n", + "-1 | \n", + "19968.0 | \n", + "116.0 | \n", + "4 | \n", + "
40000 rows × 5 columns
\n", + "