diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index b48c3ef..30c5d73 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -13,10 +13,10 @@ on:
jobs:
build:
- runs-on: ubuntu-18.04
+ runs-on: ubuntu-latest
strategy:
matrix:
- python-version: [3.7]
+ python-version: [3.9]
steps:
- uses: actions/checkout@v2
@@ -30,7 +30,6 @@ jobs:
pip install flake8 pytest
pip install fsspec>=0.3.3
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
- pip install codecov
pip install pytest-cov
pip install pytest-dependency
pip install nbformat
diff --git a/Exercise_notebooks/On_topic/06_Functions/04-riddles_and_functions_group_exercises.ipynb b/Exercise_notebooks/On_topic/06_Functions/04-riddles_and_functions_group_exercises.ipynb
index 9dd2b08..4ca4693 100644
--- a/Exercise_notebooks/On_topic/06_Functions/04-riddles_and_functions_group_exercises.ipynb
+++ b/Exercise_notebooks/On_topic/06_Functions/04-riddles_and_functions_group_exercises.ipynb
@@ -17,7 +17,6 @@
]
},
{
- "attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -46,7 +45,7 @@
"outputs": [],
"source": [
"# test if your functions works with the code below\n",
- "if is_present_today('NotaName') is True:\n",
+ "if is_present_today('NotaName') is False:\n",
" print('works!')\n",
" \n",
"if is_present_today('Petra') or is_present_today('Onno'):\n",
@@ -266,9 +265,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.6"
+ "version": "3.8.6"
}
},
"nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
}
diff --git a/practical_examples/01_GIS/02_Delfland_waterways/Delfland_waterways.ipynb b/practical_examples/01_GIS/02_Delfland_waterways/Delfland_waterways.ipynb
index 4b2e73e..f5480c4 100644
--- a/practical_examples/01_GIS/02_Delfland_waterways/Delfland_waterways.ipynb
+++ b/practical_examples/01_GIS/02_Delfland_waterways/Delfland_waterways.ipynb
@@ -1,7 +1,6 @@
{
"cells": [
{
- "attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -36,7 +35,6 @@
]
},
{
- "attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -50,10 +48,10 @@
"outputs": [],
"source": [
"# read shapefile with the actual location of the canals\n",
- "boezem = r\"shapefiles\\boezemwatergangen.shp\"\n",
+ "boezem = r\"shapefiles/boezemwatergangen.shp\"\n",
"\n",
"# read shapefile with the modelled canals\n",
- "RTCtakken = r\"shapefiles\\RTC takken voorstel 20160203.shp\"\n",
+ "RTCtakken = r\"shapefiles/RTC takken voorstel 20160203.shp\"\n",
"\n",
"# read csv file with initial water levels\n",
"csv_file = 'timeseries_0000.csv'\n",
@@ -68,7 +66,6 @@
]
},
{
- "attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -101,7 +98,6 @@
]
},
{
- "attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -128,7 +124,6 @@
]
},
{
- "attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -155,7 +150,6 @@
]
},
{
- "attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -177,7 +171,6 @@
]
},
{
- "attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -193,13 +186,20 @@
"gdf_no_x_y = gdf[['w_level', 'geometry']]\n",
"\n",
"gdf_no_x_y.to_crs(epsg= ref_basemap)\n",
- "gdf_no_x_y.explore()\n"
+ "gdf_no_x_y.explore()"
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
}
],
"metadata": {
"kernelspec": {
- "display_name": "Python 3 (ipykernel)",
+ "display_name": "Python 3",
"language": "python",
"name": "python3"
},
@@ -213,9 +213,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.10.6"
+ "version": "3.8.6"
}
},
"nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
}
diff --git a/practical_examples/02_data_analysis/03_congress_twitter_analysis/congress_twitter_analysis.ipynb b/practical_examples/02_data_analysis/03_congress_twitter_analysis/congress_twitter_analysis.ipynb
index fa455a1..a4369a1 100644
--- a/practical_examples/02_data_analysis/03_congress_twitter_analysis/congress_twitter_analysis.ipynb
+++ b/practical_examples/02_data_analysis/03_congress_twitter_analysis/congress_twitter_analysis.ipynb
@@ -41,9 +41,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Anaconda3\\envs\\dev\\lib\\site-packages\\pandas\\core\\computation\\expressions.py:20: UserWarning: Pandas requires version '2.7.3' or newer of 'numexpr' (version '2.7.1' currently installed).\n",
+ " from pandas.core.computation.check import NUMEXPR_INSTALLED\n"
+ ]
+ }
+ ],
"source": [
"import pandas as pd\n",
"#You most likely do not have textblob in you anaconda. \n",
@@ -59,7 +68,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@@ -78,7 +87,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@@ -89,11 +98,33 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 4,
"metadata": {
"scrolled": true
},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "downloading data from 2020-01-01\n",
+ "downloading data from 2020-01-02\n",
+ "downloading data from 2020-01-03\n",
+ "downloading data from 2020-01-04\n",
+ "downloading data from 2020-01-05\n",
+ "downloading data from 2020-01-06\n",
+ "downloading data from 2020-01-07\n",
+ "downloading data from 2020-01-08\n",
+ "downloading data from 2020-01-09\n",
+ "downloading data from 2020-01-10\n",
+ "downloading data from 2020-01-11\n",
+ "downloading data from 2020-01-12\n",
+ "downloading data from 2020-01-13\n",
+ "downloading data from 2020-01-14\n",
+ "downloading data from 2020-01-15\n"
+ ]
+ }
+ ],
"source": [
"twitter_data = pd.DataFrame()\n",
"for date in date_range:\n",
@@ -119,7 +150,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
@@ -129,7 +160,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
@@ -150,7 +181,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
@@ -168,18 +199,17 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"#make sure the index is sorted and datetime datatype\n",
- "twitter_data.sort_index(inplace=True)\n",
- "twitter_data.index = twitter_data.index.astype('datetime64[ns]')"
+ "twitter_data.sort_index(inplace=True)"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
@@ -190,7 +220,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
@@ -200,16 +230,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "twitter_data.loc['2020-01-10']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
+ "execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
@@ -224,7 +245,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
@@ -234,13 +255,13 @@
"\n",
"#Note, in de lines below the 'D' stands for daily instead of 'democrat'. \n",
"#This does not improve readibility, but ah well. \n",
- "twitter_data_d_daily_average = twitter_data_d.resample('D').mean()\n",
- "twitter_data_r_daily_average = twitter_data_r.resample('D').mean()"
+ "twitter_data_d_daily_average = twitter_data_d['polarity'].resample('D').mean()\n",
+ "twitter_data_r_daily_average = twitter_data_r['polarity'].resample('D').mean()"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 14,
"metadata": {
"scrolled": true
},
@@ -251,10 +272,10 @@
"lower_percentile = 10\n",
"\n",
"#With apply we do the operation per row of echt dataframe\n",
- "twitter_data_d_daily_upper = twitter_data_d.resample('D').quantile(upper_percentile/100)['polarity']\n",
- "twitter_data_d_daily_lower = twitter_data_d.resample('D').quantile(lower_percentile/100)['polarity']\n",
- "twitter_data_r_daily_upper = twitter_data_r.resample('D').quantile(upper_percentile/100)['polarity']\n",
- "twitter_data_r_daily_lower = twitter_data_r.resample('D').quantile(lower_percentile/100)['polarity']"
+ "twitter_data_d_daily_upper = twitter_data_d['polarity'].resample('D').quantile(upper_percentile/100)\n",
+ "twitter_data_d_daily_lower = twitter_data_d['polarity'].resample('D').quantile(lower_percentile/100)\n",
+ "twitter_data_r_daily_upper = twitter_data_r['polarity'].resample('D').quantile(upper_percentile/100)\n",
+ "twitter_data_r_daily_lower = twitter_data_r['polarity'].resample('D').quantile(lower_percentile/100)"
]
},
{
@@ -266,14 +287,30 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 15,
"metadata": {
"scrolled": true
},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "minimum\n",
+ "lowest, average polarity of twitter users: -0.50\n",
+ "twitter user with lowest average polarity: JimPressOffice\n",
+ "number of tweets by JimPressOffice : 1\n",
+ "\n",
+ "maximum\n",
+ "maximum, average polarity of twitter users: 1.00\n",
+ "twitter user with maximum average polarity: latta4congress\n",
+ "number of tweets by latta4congress : 1\n"
+ ]
+ }
+ ],
"source": [
"#First lets get some statistics \n",
- "df = twitter_data_rel.groupby(['screen_name']).mean()\n",
+ "df = twitter_data_rel[['screen_name', 'polarity']].groupby(['screen_name']).mean()\n",
"\n",
"low_ave_pol = df.polarity.min()\n",
"user_low_ave_pol = df[df.polarity==low_ave_pol].index[0]\n",
@@ -293,7 +330,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
@@ -318,20 +355,82 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 18,
"metadata": {},
- "outputs": [],
- "source": [
- "twitter_data_rel.loc['2020-01-02']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {
- "scrolled": false
- },
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " polarity | \n",
+ "
\n",
+ " \n",
+ " | party_mod | \n",
+ " | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | Democrat | \n",
+ " 0.123038 | \n",
+ "
\n",
+ " \n",
+ " | Republican | \n",
+ " 0.145325 | \n",
+ "
\n",
+ " \n",
+ " | Other | \n",
+ " 0.135987 | \n",
+ "
\n",
+ " \n",
+ " | Total | \n",
+ " 0.134045 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "