{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Popular Data Science Questions" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Our goal in this project is to use [Data Science Stack Exchange](https://datascience.stackexchange.com) to determine what content should a data science education company create, based on interest by subject." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Stack Exchange" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### What kind of questions are welcome on this site?\n", "\n", "On DSSE's help center's [section on questions](https://datascience.stackexchange.com/help/asking) , we can read that we should:\n", "\n", "* Avoid subjective questions.\n", "* Ask practical questions about Data Science — there are adequate sites for theoretical questions.\n", "* Ask specific questions.\n", "* Make questions relevant to others.\n", "\n", "All of these characteristics, if employed, should be helpful attributes to our goal.\n", "\n", "In the help center we also learned that in addition to the sites mentioned in the _Learn_ section, there are other two sites that are relevant:\n", "\n", "* [Open Data](https://opendata.stackexchange.com/help/on-topic) (Dataset requests)\n", "* [Computational Science](https://scicomp.stackexchange.com/help/on-topic) (Software packages and algorithms in applied mathematics)\n", "\n", "#### What, other than questions, does DSSE's [home](https://datascience.stackexchange.com) subdivide into?\n", "\n", "On the [home page](https://datascience.stackexchange.com/) we can see that we have four sections:\n", "\n", "* [Questions](https://datascience.stackexchange.com/questions) — a list of all questions asked;\n", "* [Tags](https://datascience.stackexchange.com/tags) — a list of tags (keywords or labels that categorize questions);\n", "\n", " ![tags_ds](https://dq-content.s3.amazonaws.com/469/tags_ds.png)\n", "* [Users](https://datascience.stackexchange.com/users) — a list of users;\n", "* [Unanswered](https://datascience.stackexchange.com/unanswered) — a list of unanswered questions;\n", "\n", "The tagging system used by Stack Exchange looks just like what we need to solve this problem as it allow us to quantify how many questions are asked about each subject.\n", "\n", "Something else we can learn from exploring the help center, is that Stack Exchange's sites are heavily moderated by the community; this gives us some confidence in using the tagging system to derive conclusions.\n", "\n", "#### What information is available in each post?\n", "\n", "Looking, just as an example, at [this](https://datascience.stackexchange.com/questions/19141/linear-model-to-generate-probability-of-each-possible-output?rq=1) question, some of the information we see is:\n", "\n", "* For both questions and answers:\n", " * The posts's score;\n", " * The posts's title;\n", " * The posts's author;\n", " * The posts's body;\n", "* For questions only:\n", " * How many users have it on their \"\n", " * The last time the question as active;\n", " * How many times the question was viewed;\n", " * Related questions;\n", " * The question's tags;\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Stack Exchange Data Explorer\n", "\n", "Perusing the table names, a few stand out as relevant for our goal:\n", "\n", "* Posts\n", "* PostTags\n", "* Tags\n", "* TagSynonyms\n", "\n", "Running a few exploratory queries, leads us to focus our efforts on `Posts` table. For examples, the `Tags` table looked very promising as it tells us how many times each tag was used, but there's no way to tell just from this if the interest in these tags is recent or a thing from the past.\n", "\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
IdTagNameCountExcerptPostIdWikiPostId
2machine-learning691949094908
46python390755235522
81neural-network292388858884
194deep-learning278689568955
77classification189949114910
324keras173692519250
128scikit-learn130358965895
321tensorflow122491839182
47nlp1162147146
24r11144948
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Getting the Data\n", "\n", "To get the relevant data we run the following query.\n", "\n", "```\n", "SELECT Id, CreationDate,\n", " Score, ViewCount, Tags,\n", " AnswerCount, FavoriteCount\n", " FROM posts\n", " WHERE PostTypeId = 1 AND YEAR(CreationDate) = 2019;\n", "```\n", "\n", "Here's what the first few rows look like:\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
IdPostTypeIdCreationDateScoreViewCountTagsAnswerCountFavoriteCount
4441912019-01-23 09:21:13121<machine-learning><data-mining>0
4442012019-01-23 09:34:01025<machine-learning><regression><linear-regression><regularization>0
4442312019-01-23 09:58:4121651<python><time-series><forecast><forecasting>0
4442712019-01-23 10:57:09055<machine-learning><scikit-learn><pca>1
4442812019-01-23 11:02:15019<dataset><bigdata><data><speech-to-text>0
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Exploring the Data\n", "\n", "We can read in the data while immediately making sure `CreationDate` will be stored as a datetime object:" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "# We import everything that we'll use\n", "\n", "import pandas as pd\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "%matplotlib inline" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "questions = pd.read_csv(\"2019_questions.csv\", parse_dates=[\"CreationDate\"])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Running [`questions.info()`](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.info.html) should gives a lot of useful information." ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 8839 entries, 0 to 8838\n", "Data columns (total 7 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 Id 8839 non-null int64 \n", " 1 CreationDate 8839 non-null datetime64[ns]\n", " 2 Score 8839 non-null int64 \n", " 3 ViewCount 8839 non-null int64 \n", " 4 Tags 8839 non-null object \n", " 5 AnswerCount 8839 non-null int64 \n", " 6 FavoriteCount 1407 non-null float64 \n", "dtypes: datetime64[ns](1), float64(1), int64(4), object(1)\n", "memory usage: 483.5+ KB\n" ] } ], "source": [ "questions.info()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We see that only `FavoriteCount` has missing values. A missing value on this column probably means that the question was is not present in any users' favorite list, so we can replace the missing values with zero.\n", "\n", "The types seem adequate for every column, however, after we fill in the missing values on `FavoriteCount`, there is no reason to store the values as floats.\n", "\n", "Since the `object` dtype is a catch-all type, let's see what types the objects in `questions[\"Tags\"]` are." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([], dtype=object)" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "questions[\"Tags\"].apply(lambda value: type(value)).unique()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We see that every value in this column is a string. On Stack Exchange, each question can only have a maximum of five tags ([source](https://meta.stackexchange.com/a/18879)), so one way to deal with this column is to create five columns in `questions` called `Tag1`, `Tag2`, `Tag3`, `Tag4`, and `Tag5` and populate the columns with the tags in each row.\n", "\n", "However, since doesn't help is relating tags from one question to another, we'll just keep them as a list." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Cleaning the Data\n", "\n", "We'll begin by fixing `FavoriteCount`." ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Id int64\n", "CreationDate datetime64[ns]\n", "Score int64\n", "ViewCount int64\n", "Tags object\n", "AnswerCount int64\n", "FavoriteCount int64\n", "dtype: object" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "questions.fillna(value={\"FavoriteCount\": 0}, inplace=True)\n", "questions[\"FavoriteCount\"] = questions[\"FavoriteCount\"].astype(int)\n", "questions.dtypes" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's now modify `Tags` to make it easier to work with." ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
IdCreationDateScoreViewCountTagsAnswerCountFavoriteCount
511563822019-07-25 15:00:20034[machine-learning, python, pandas, natural-lan...00
2178583122019-08-28 09:44:00141[neural-network, pytorch]01
2536581512019-08-25 01:01:29037[dataset, audio-recognition]20
\n", "
" ], "text/plain": [ " Id CreationDate Score ViewCount \\\n", "511 56382 2019-07-25 15:00:20 0 34 \n", "2178 58312 2019-08-28 09:44:00 1 41 \n", "2536 58151 2019-08-25 01:01:29 0 37 \n", "\n", " Tags AnswerCount \\\n", "511 [machine-learning, python, pandas, natural-lan... 0 \n", "2178 [neural-network, pytorch] 0 \n", "2536 [dataset, audio-recognition] 2 \n", "\n", " FavoriteCount \n", "511 0 \n", "2178 1 \n", "2536 0 " ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "questions[\"Tags\"] = questions[\"Tags\"].str.replace(\"^<|>$\", \"\").str.split(\"><\")\n", "questions.sample(3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Most Used and Most Viewed\n", "\n", "We'll begin by counting how many times each tag was used" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "tag_count = dict()\n", "\n", "for tags in questions[\"Tags\"]:\n", " for tag in tags:\n", " if tag in tag_count:\n", " tag_count[tag] += 1\n", " else:\n", " tag_count[tag] = 1" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For improved aesthetics, let's transform `tag_count` in a dataframe." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Count
machine-learning2693
data-mining217
regression347
linear-regression175
regularization50
python1814
time-series466
forecast34
forecasting85
scikit-learn540
\n", "
" ], "text/plain": [ " Count\n", "machine-learning 2693\n", "data-mining 217\n", "regression 347\n", "linear-regression 175\n", "regularization 50\n", "python 1814\n", "time-series 466\n", "forecast 34\n", "forecasting 85\n", "scikit-learn 540" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tag_count = pd.DataFrame.from_dict(tag_count, orient=\"index\")\n", "tag_count.rename(columns={0: \"Count\"}, inplace=True)\n", "tag_count.head(10)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's now sort this dataframe by `Count` and visualize the top 20 results." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Count
machine-learning-model224
statistics234
clustering257
predictive-modeling265
r268
dataset340
regression347
pandas354
lstm402
time-series466
cnn489
nlp493
scikit-learn540
tensorflow584
classification685
keras935
neural-network1055
deep-learning1220
python1814
machine-learning2693
\n", "
" ], "text/plain": [ " Count\n", "machine-learning-model 224\n", "statistics 234\n", "clustering 257\n", "predictive-modeling 265\n", "r 268\n", "dataset 340\n", "regression 347\n", "pandas 354\n", "lstm 402\n", "time-series 466\n", "cnn 489\n", "nlp 493\n", "scikit-learn 540\n", "tensorflow 584\n", "classification 685\n", "keras 935\n", "neural-network 1055\n", "deep-learning 1220\n", "python 1814\n", "machine-learning 2693" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "most_used = tag_count.sort_values(by=\"Count\").tail(20)\n", "most_used" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The threshold of `20` is somewhat arbitrary and we can experiment with others, however, popularity of the tags rapidly declines, so looking at these tags should be enough to help us with our goal. Let's visualize these data." ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "most_used.plot(kind=\"barh\", figsize=(16,8))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Some tags are very, very broad and are unlikely to be useful; e.g.: `python`, `dataset`, `r`. Before we investigate the tags a little deeper, let's repeat the same process for views.\n", "\n", "We'll use _pandas_'s [`pandas.DataFrame.iterrows()`](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.iterrows.html#pandas.DataFrame.iterrows). " ] }, { "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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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "tag_view_count = dict()\n", "\n", "for index, row in questions.iterrows():\n", " for tag in row['Tags']:\n", " if tag in tag_view_count:\n", " tag_view_count[tag] += row['ViewCount']\n", " else:\n", " tag_view_count[tag] = row['ViewCount']\n", " \n", "tag_view_count = pd.DataFrame.from_dict(tag_view_count, orient=\"index\")\n", "tag_view_count.rename(columns={0: \"ViewCount\"}, inplace=True)\n", "\n", "most_viewed = tag_view_count.sort_values(by=\"ViewCount\").tail(20)\n", "\n", "most_viewed.plot(kind=\"barh\", figsize=(16,8))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's see them side by side." ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([],\n", " dtype=object)" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "fig, axes = plt.subplots(nrows=1, ncols=2)\n", "fig.set_size_inches((24, 10))\n", "most_used.plot(kind=\"barh\", ax=axes[0], subplots=True)\n", "most_viewed.plot(kind=\"barh\", ax=axes[1], subplots=True)" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "in_used = pd.merge(most_used, most_viewed, how=\"left\", left_index=True, right_index=True)\n", "in_viewed = pd.merge(most_used, most_viewed, how=\"right\", left_index=True, right_index=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Relations Between Tags" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "One way of trying to gauge how pairs of tags are related to each other, is to count how many times each pair appears together. Let's do this.\n", "\n", "We'll begin by creating a list of all tags." ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "all_tags = list(tag_count.index)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We'll now create a dataframe where each row will represent a tag, and each column as well. Something like this:\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
tag1tag2tag3
tag1
tag2
tag3
" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
machine-learningdata-miningregressionlinear-regression
machine-learningNaNNaNNaNNaN
data-miningNaNNaNNaNNaN
regressionNaNNaNNaNNaN
linear-regressionNaNNaNNaNNaN
\n", "
" ], "text/plain": [ " machine-learning data-mining regression linear-regression\n", "machine-learning NaN NaN NaN NaN\n", "data-mining NaN NaN NaN NaN\n", "regression NaN NaN NaN NaN\n", "linear-regression NaN NaN NaN NaN" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "associations = pd.DataFrame(index=all_tags, columns=all_tags)\n", "associations.iloc[0:4,0:4]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We will now fill this dataframe with zeroes and then, for each lists of tags in `questions[\"Tags\"]`, we will increment the intervening tags by one. The end result will be a dataframe that for each pair of tags, it tells us how many times they were used together." ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [], "source": [ "associations.fillna(0, inplace=True)\n", "\n", "for tags in questions[\"Tags\"]:\n", " associations.loc[tags, tags] += 1" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This dataframe is quite large. Let's focus our attention on the most used tags. We'll add some colors to make it easier to talk about the dataframe. (At the time of this writing, GitHub's renderer does not display the colors, we suggest you use this solution notebook together with [JupyterLab](https://jupyterlab.readthedocs.io/en/stable/))." ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
machine-learning-model statistics clustering predictive-modeling r dataset regression pandas lstm time-series cnn nlp scikit-learn tensorflow classification keras neural-network deep-learning python machine-learning
machine-learning-model22433217128457441892117101937139
statistics32343161617163122136019311123589
clustering3325701652532009240120824561
predictive-modeling211602651372841331611262711133235123
r7161613268610232224111010952463
dataset121757634061476111199281320325399
regression81622810634761124623793431422159119
pandas4354214635471913373331124462
lstm513133711740287241924320133691036171
time-series72220312262419874668012925513344105131
cnn41062116124848970572011611816062124
nlp439141123190749312113523247271113
scikit-learn18624121937372120125401547342416235188
tensorflow9006199343957111558420256108136167106
classification21191227102834320252035472068558655998259
keras173011101331313351116233425658935235247280195
neural-network101181392042169331182424108652351055305137366
deep-learning1912232532211103441607216136592473051220160429
python37354535245359244611056271235167982801371601814499
machine-learning1398961123639911962711311241131881062591953664294992693
" ], "text/plain": [ "" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "relations_most_used = associations.loc[most_used.index, most_used.index]\n", "\n", "def style_cells(x):\n", " helper_df = pd.DataFrame('', index=x.index, columns=x.columns)\n", " helper_df.loc[\"time-series\", \"r\"] = \"background-color: yellow\"\n", " helper_df.loc[\"r\", \"time-series\"] = \"background-color: yellow\"\n", " for k in range(helper_df.shape[0]):\n", " helper_df.iloc[k,k] = \"color: blue\"\n", " \n", " return helper_df\n", "\n", "relations_most_used.style.apply(style_cells, axis=None)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The cells highlighted in yellow tell us that `time-series` was used together with `r` 22 times. The values in blue tell us how many times each of the tags was used. We saw earlier that `machine-learning` was used 2693 times and we confirm it in this dataframe.\n", "\n", "It's hard for a human to understand what is going on in this dataframe. Let's create a heatmap. But before we do it, let's get rid of the values in blue, otherwise the colors will be too skewed." ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [], "source": [ "for i in range(relations_most_used.shape[0]):\n", " relations_most_used.iloc[i,i] = pd.np.NaN" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.figure(figsize=(12,8))\n", "sns.heatmap(relations_most_used, cmap=\"Greens\", annot=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The most used tags also seem to have the strongest relationships, as given by the dark concentration in the bottom right corner. However, this could simply be because each of these tags is used a lot, and so end up being used together a lot without possibly even having any strong relation between them.\n", "\n", "A more intuitive manifestation of this phenomenon is the following. A lot of people buy bread, a lot of people buy toilet paper, so they end up being purchased together a lot, but purchasing one of them doesn't increase the chances of purchasing the other." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Another shortcoming of this attempt is that it only looks at relations between pairs of tags and not between multiple groups of tags. For example, it could be the case that when used together, `dataset` and `scikit-learn` have a \"strong\" relation to `pandas`, but each by itself doesn't.\n", "\n", "So how do we attack both these problems? There is a powerful data mining technique that allows us to handle this: [association rules](https://en.wikipedia.org/wiki/Association_rule_learning). Association rules allow us to analytically spot relations like \"people who purchase milk, also purchase eggs\". Moreover, we can also measure how strong this relations are on several fronts: how common the relation is, how strong it is, and how independent the components of the relationship are (toilet paper and bread are probably more independent than eggs and milk — you'll learn more about [statistical independence](https://en.wikipedia.org/wiki/Independence_(probability_theory)) in the next step).\n", "\n", "\n", "We won't get into the details of it, as the technique is out of scope for this course, but it is a path worth investigating!" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Enter Domain Knowledge\n", "\n", "[Keras](https://keras.io/), [scikit-learn](https://scikit-learn.org/), [TensorFlow](https://www.tensorflow.org/) are all Python libraries that allow their users to employ deep learning (a type of neural network).\n", "\n", "Most of the top tags are all intimately related with one central machine learning theme: deep learning. If we want to be very specific, we can suggest the creation of Python content that uses deep learning for classification problems (and other variations of this suggestion).\n", "\n", "At the glance of an eye, someone with sufficient domain knowledge can tell that the most popular topic at the moment, as shown by our analysis, is deep learning." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Just a Fad?\n", "\n", "Let's read in the file into a dataframe called `all_q`. We'll parse the dates at read-time." ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [], "source": [ "all_q = pd.read_csv(\"all_questions.csv\", parse_dates=[\"CreationDate\"])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can use the same technique as before to clean the tags column." ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "all_q[\"Tags\"] = all_q[\"Tags\"].str.replace(\"^<|>$\", \"\").str.split(\"><\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Before deciding which questions should be classified as being deep learning questions, we should decide what tags are deep learning tags.\n", "\n", "The definition of what constitutes a deep learning tag we'll use is: a tag that belongs to the list `[\"lstm\", \"cnn\", \"scikit-learn\", \"tensorflow\", \"keras\", \"neural-network\", \"deep-learning\"]`.\n", "\n", "This list was obtained by looking at all the tags in `most_used` and seeing which ones had any relation to deep learning. You can use Google and read the tags descriptions to reach similar results.\n", "\n", "We'll now create a function that assigns `1` to deep learning questions and `0` otherwise; and we use it." ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "def class_deep_learning(tags):\n", " for tag in tags:\n", " if tag in [\"lstm\", \"cnn\", \"scikit-learn\", \"tensorflow\",\n", " \"keras\", \"neural-network\", \"deep-learning\"]:\n", " return 1\n", " return 0" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [], "source": [ "all_q[\"DeepLearning\"] = all_q[\"Tags\"].apply(class_deep_learning)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
IdCreationDateTagsDeepLearning
15231446752019-01-28 06:20:18[model-selection]0
440556392019-07-14 11:45:43[machine-learning, dataset, machine-learning-m...0
11720515232019-05-07 04:57:35[neural-network, gradient-descent, batch-norma...1
6262272322018-01-30 09:53:38[python, convergence]0
19292649302019-12-16 14:38:17[neural-network, deep-learning, keras, convolu...1
\n", "
" ], "text/plain": [ " Id CreationDate \\\n", "15231 44675 2019-01-28 06:20:18 \n", "440 55639 2019-07-14 11:45:43 \n", "11720 51523 2019-05-07 04:57:35 \n", "6262 27232 2018-01-30 09:53:38 \n", "19292 64930 2019-12-16 14:38:17 \n", "\n", " Tags DeepLearning \n", "15231 [model-selection] 0 \n", "440 [machine-learning, dataset, machine-learning-m... 0 \n", "11720 [neural-network, gradient-descent, batch-norma... 1 \n", "6262 [python, convergence] 0 \n", "19292 [neural-network, deep-learning, keras, convolu... 1 " ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "all_q.sample(5)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Looks good!" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The data-science-techonology landscape isn't something as dynamic to merit daily, weekly, or even monthly tracking. Let's track it quarterly.\n", "\n", "Since we don't have all the data for the first quarter of 2020, we'll get rid of those dates:" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [], "source": [ "all_q = all_q[all_q[\"CreationDate\"].dt.year < 2020]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's create a column that identifies the quarter in which a question was asked." ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [], "source": [ "def fetch_quarter(datetime):\n", " year = str(datetime.year)[-2:]\n", " quarter = str(((datetime.month-1) // 3) + 1)\n", " return \"{y}Q{q}\".format(y=year, q=quarter)\n", "\n", "all_q[\"Quarter\"] = all_q[\"CreationDate\"].apply(fetch_quarter)" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
IdCreationDateTagsDeepLearningQuarter
0454162019-02-12 00:36:29[python, keras, tensorflow, cnn, probability]119Q1
1454182019-02-12 00:50:39[neural-network]119Q1
2454222019-02-12 04:40:51[python, ibm-watson, chatbot]019Q1
3454262019-02-12 04:51:49[keras]119Q1
4454272019-02-12 05:08:24[r, predictive-modeling, machine-learning-mode...019Q1
\n", "
" ], "text/plain": [ " Id CreationDate \\\n", "0 45416 2019-02-12 00:36:29 \n", "1 45418 2019-02-12 00:50:39 \n", "2 45422 2019-02-12 04:40:51 \n", "3 45426 2019-02-12 04:51:49 \n", "4 45427 2019-02-12 05:08:24 \n", "\n", " Tags DeepLearning Quarter \n", "0 [python, keras, tensorflow, cnn, probability] 1 19Q1 \n", "1 [neural-network] 1 19Q1 \n", "2 [python, ibm-watson, chatbot] 0 19Q1 \n", "3 [keras] 1 19Q1 \n", "4 [r, predictive-modeling, machine-learning-mode... 0 19Q1 " ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "all_q.head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For the final stretch of this screen, we'll group by quarter and:\n", "\n", "* Count the number of deep learning questions.\n", "* Count the total number of questions.\n", "* Compute the ratio between the two numbers above." ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
QuarterDeepLearningQuestionsTotalQuestionsDeepLearningRate
1718Q368515120.453042
716Q11105160.213178
615Q4663820.172775
2219Q480920360.397348
916Q31615850.275214
\n", "
" ], "text/plain": [ " Quarter DeepLearningQuestions TotalQuestions DeepLearningRate\n", "17 18Q3 685 1512 0.453042\n", "7 16Q1 110 516 0.213178\n", "6 15Q4 66 382 0.172775\n", "22 19Q4 809 2036 0.397348\n", "9 16Q3 161 585 0.275214" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "quarterly = all_q.groupby('Quarter').agg({\"DeepLearning\": ['sum', 'size']})\n", "quarterly.columns = ['DeepLearningQuestions', 'TotalQuestions']\n", "quarterly[\"DeepLearningRate\"] = quarterly[\"DeepLearningQuestions\"]\\\n", " /quarterly[\"TotalQuestions\"]\n", "# The following is done to help with visualizations later.\n", "quarterly.reset_index(inplace=True)\n", "quarterly.sample(5)" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "ax1 = quarterly.plot(x=\"Quarter\", y=\"DeepLearningRate\",\n", " kind=\"line\", linestyle=\"-\", marker=\"o\", color=\"orange\",\n", " figsize=(24,12)\n", " )\n", "\n", "ax2 = quarterly.plot(x=\"Quarter\", y=\"TotalQuestions\",\n", " kind=\"bar\", ax=ax1, secondary_y=True, alpha=0.7, rot=45)\n", "\n", "for idx, t in quarterly[\"TotalQuestions\"].iteritems():\n", " ax2.text(idx, t, str(t), ha=\"center\", va=\"bottom\")\n", "xlims = ax1.get_xlim()\n", "\n", "ax1.get_legend().remove()\n", "\n", "handles1, labels1 = ax1.get_legend_handles_labels()\n", "handles2, labels2 = ax2.get_legend_handles_labels()\n", "ax1.legend(handles=handles1 + handles2,\n", " labels=labels1 + labels2,\n", " loc=\"upper left\", prop={\"size\": 12})\n", "\n", "\n", "for ax in (ax1, ax2):\n", " for where in (\"top\", \"right\"):\n", " ax.spines[where].set_visible(False)\n", " ax.tick_params(right=False, labelright=False)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "It seems that deep learning questions was a high-growth trend since the start of DSSE and it looks like it is plateauing. There is no evidence to suggest that interest in deep learning is decreasing and so we maintain our previous idea of proposing that we create deep learning content." ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.7.6" } }, "nbformat": 4, "nbformat_minor": 4 }