Merge branch 'more_stats' into 'master'

more ossr stats in doc See merge request !253

Merge branch 'more_stats' into 'master'
e6778527 · Vuillaume · f5f87f0b · 2397761e · e6778527 · e6778527
Commit e6778527 authored 2 years ago by Vuillaume
--- a/docs/doc_requirements.txt
+++ b/docs/doc_requirements.txt
@@ -9,3 +9,4 @@ sphinxcontrib-autoprogram
 ipython_genutils
 sphinxcontrib-mermaid
 docutils>=0.17
+wordcloud
--- a/docs/notebooks/ossr_statistics.ipynb
+++ b/docs/notebooks/ossr_statistics.ipynb
@@ -19,7 +19,19 @@
   "source": [
    "from eossr.api import get_ossr_records, get_zenodo_records\n",
    "from IPython.display import Markdown as md\n",
-    "from datetime import date"
+    "from datetime import date\n",
+    "import itertools\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "32b381a7-ff5a-4c56-919a-d47ecdbec6bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.style.use('seaborn-v0_8-colorblind')"
   ]
  },
  {
@@ -43,6 +55,56 @@
    "    \n"
   ]
  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e71a35a5-8afa-466a-a2e6-424ff8d07611",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "from collections import Counter\n",
+    "from wordcloud import WordCloud\n",
+    "\n",
+    "def create_pie_chart(occurrences, ax=None):\n",
+    "    # Get the counts of each occurrence\n",
+    "    counts = Counter(occurrences)\n",
+    "\n",
+    "    ax = plt.gca() if ax is None else ax\n",
+    "\n",
+    "    # Create the pie chart\n",
+    "    ax.pie(list(counts.values()), labels=list(counts.keys()), autopct='%1.1f%%', startangle=90)\n",
+    "\n",
+    "    # Show the chart\n",
+    "    return ax\n",
+    "\n",
+    "\n",
+    "def create_word_cloud(words):\n",
+    "    # Generate a word frequency dictionary\n",
+    "    word_freq = {}\n",
+    "    for word in words:\n",
+    "        word = word.upper()\n",
+    "        word_freq[word] = word_freq.get(word, 0) + 1\n",
+    "\n",
+    "    # Create a word cloud object\n",
+    "    wordcloud = WordCloud(width=1000, height=600, background_color='white', stopwords=set()).generate_from_frequencies(word_freq)\n",
+    "\n",
+    "    # Plot the word cloud\n",
+    "    fig = plt.figure(figsize=(10, 6), facecolor=None)\n",
+    "    plt.imshow(wordcloud)\n",
+    "    plt.axis(\"off\")\n",
+    "    plt.tight_layout(pad=0)\n",
+    "    return fig\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b9992892-a857-46a4-adc9-2a18f2889e35",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
  {
   "cell_type": "code",
   "execution_count": null,
@@ -79,6 +141,68 @@
    "text += f\"You may find them [directly on Zenodo]({url_escape2020_not_ossr})\"\n"
   ]
  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a4290b16-8e72-4fbe-96e7-758c3a113fd7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "md(\"## Distribution of licenses in the OSSR\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ab7ff264-055e-4a64-b4b5-968f1e4b38b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "licenses = [record.metadata['license']['id'] for record in ossr_records]\n",
+    "\n",
+    "plt.figure(figsize=(7,7))\n",
+    "create_pie_chart(licenses);"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e653506a-64ee-4bd5-8c93-6cfe997d7319",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "md(\"## Cloud of OSSR keywords\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7676462b-64a0-49ab-aa59-72945a0a5024",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "keywords = [record.metadata['keywords'] for record in ossr_records if 'keywords' in record.metadata]\n",
+    "keywords = list(itertools.chain(*keywords))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "750351bd-f043-4f3a-a8e2-0dee8afed6ae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig = create_word_cloud(keywords)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8cc6ae00-b2e3-4ee2-ba1c-373ff9cf0d6f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
  {
   "cell_type": "code",
   "execution_count": null,
@@ -101,7 +225,7 @@
 "metadata": {
  "celltoolbar": "Éditer les Méta-Données",
  "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
@@ -115,7 +239,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.9.2"
+   "version": "3.10.4"
  }
 },
 "nbformat": 4,

 %% Cell type:markdown id:6f9a9077 tags:

 # OSSR Statistics

 %% Cell type:code id:dbb762f7 tags:

 ``` python
 from eossr.api import get_ossr_records, get_zenodo_records
 from IPython.display import Markdown as md
 from datetime import date
+import itertools
+import matplotlib.pyplot as plt
+```
+
+%% Cell type:code id:32b381a7-ff5a-4c56-919a-d47ecdbec6bd tags:
+
+``` python
+plt.style.use('seaborn-v0_8-colorblind')
 ```

 %% Cell type:code id:b9668e64 tags:

 ``` python
 title = f"## OSSR statistics generated the {date.today()}"

 ossr_records = get_ossr_records()
 stats_names = ['downloads', 'unique_downloads', 'views', 'unique_views', ]
 sum_stats = {key: sum([int(rec.data['stats'][key]) for rec in ossr_records]) for key in stats_names}

 text = f"## There are {len(ossr_records)} records in the OSSR.\n"
 for key, value in sum_stats.items():
    text+=f"{key.replace('_', ' ')}: {value}\n\n"

 ```

+%% Cell type:code id:e71a35a5-8afa-466a-a2e6-424ff8d07611 tags:
+
+``` python
+import matplotlib.pyplot as plt
+from collections import Counter
+from wordcloud import WordCloud
+
+def create_pie_chart(occurrences, ax=None):
+    # Get the counts of each occurrence
+    counts = Counter(occurrences)
+
+    ax = plt.gca() if ax is None else ax
+
+    # Create the pie chart
+    ax.pie(list(counts.values()), labels=list(counts.keys()), autopct='%1.1f%%', startangle=90)
+
+    # Show the chart
+    return ax
+
+
+def create_word_cloud(words):
+    # Generate a word frequency dictionary
+    word_freq = {}
+    for word in words:
+        word = word.upper()
+        word_freq[word] = word_freq.get(word, 0) + 1
+
+    # Create a word cloud object
+    wordcloud = WordCloud(width=1000, height=600, background_color='white', stopwords=set()).generate_from_frequencies(word_freq)
+
+    # Plot the word cloud
+    fig = plt.figure(figsize=(10, 6), facecolor=None)
+    plt.imshow(wordcloud)
+    plt.axis("off")
+    plt.tight_layout(pad=0)
+    return fig
+```
+
+%% Cell type:code id:b9992892-a857-46a4-adc9-2a18f2889e35 tags:
+
+``` python
+```
+
 %% Cell type:code id:fe656e0b tags:

 ``` python
 md(title)
 ```

 %% Cell type:code id:df351e32 tags:

 ``` python
 md(text)
 ```

 %% Cell type:code id:d0e84058 tags:

 ``` python
 escape2020_community_records = get_zenodo_records(communities='escape2020')

 url_escape2020_not_ossr = 'https://zenodo.org/communities/escape2020/search?page=1&size=20&q=&type=publication&type=lesson&type=poster'
 text = f"**Note that there are also {len(escape2020_community_records) - len(ossr_records)} records in the `escape2020` community that are not software or datasets.**\n\n"
 text += f"You may find them [directly on Zenodo]({url_escape2020_not_ossr})"
 ```

+%% Cell type:code id:a4290b16-8e72-4fbe-96e7-758c3a113fd7 tags:
+
+``` python
+md("## Distribution of licenses in the OSSR")
+```
+
+%% Cell type:code id:ab7ff264-055e-4a64-b4b5-968f1e4b38b6 tags:
+
+``` python
+licenses = [record.metadata['license']['id'] for record in ossr_records]
+
+plt.figure(figsize=(7,7))
+create_pie_chart(licenses);
+```
+
+%% Cell type:code id:e653506a-64ee-4bd5-8c93-6cfe997d7319 tags:
+
+``` python
+md("## Cloud of OSSR keywords")
+```
+
+%% Cell type:code id:7676462b-64a0-49ab-aa59-72945a0a5024 tags:
+
+``` python
+keywords = [record.metadata['keywords'] for record in ossr_records if 'keywords' in record.metadata]
+keywords = list(itertools.chain(*keywords))
+```
+
+%% Cell type:code id:750351bd-f043-4f3a-a8e2-0dee8afed6ae tags:
+
+``` python
+fig = create_word_cloud(keywords)
+```
+
+%% Cell type:code id:8cc6ae00-b2e3-4ee2-ba1c-373ff9cf0d6f tags:
+
+``` python
+```
+
 %% Cell type:code id:696416cf tags:

 ``` python
 md(text)
 ```

 %% Cell type:code id:ae5204cf tags:

 ``` python
 ```