├── Avenir.ttc ├── README.md ├── TidyTuesday01022022.ipynb ├── TidyTuesday01032022.ipynb ├── TidyTuesday02082022.ipynb ├── TidyTuesday03052022.ipynb ├── TidyTuesday05072022.ipynb ├── TidyTuesday07062022.ipynb ├── TidyTuesday08022022.ipynb ├── TidyTuesday12072022.ipynb ├── TidyTuesday140622.ipynb ├── TidyTuesday17052022.ipynb ├── TidyTuesday19072022.ipynb ├── TidyTuesday21062022.ipynb ├── TidyTuesday22022022.ipynb ├── TidyTuesday22032022.ipynb ├── TidyTuesday24052022.ipynb ├── TidyTuesday28062022.ipynb └── TidyTuesday29032022.ipynb /Avenir.ttc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xh313/TidyTuesdayWithPython/07be77cb1bc7d8b367265e929c3cb662074d3eff/Avenir.ttc -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Tidy Tuesday with Python 2 | My weekly (or monthly) data visualisation practicing using data from TidyTuesday, using Matplotlib and Python instead of R! 3 | 4 | # Projects 5 | 6 | ## 2 Aug 2022 7 | Frogs spotted in Oregon. I experimented with circle packing but it's so much pain that I would probably never do it again. 8 | Anyway here's the code and the pic. 9 | 10 | ![frogs](https://user-images.githubusercontent.com/77285010/182714887-54e0da04-e166-4494-9ba3-f829796f83d2.png) 11 | 12 | 13 | Code: [Here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday02082022.ipynb) 14 | 15 | ## 19 Jul 2022 16 | This data set is so interesting that I got so obsessed with wrangling it and forgot about visualisation... 17 | 18 | Here is a meaningless graph just for fun XD 19 | 20 | ![image](https://user-images.githubusercontent.com/77285010/180100441-960b7acb-c61a-4dc2-b882-1a4fecb0b45e.png) 21 | 22 | Code: [Here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday19072022.ipynb) 23 | 24 | ## 12 Jul 2022 25 | European flights. I don't know what I'm doing. Ideally this highlights the hit of COVID on air traffic. 26 | 27 | ![image](https://user-images.githubusercontent.com/77285010/178685955-5d32be39-3327-4355-8e84-682df76e9e95.png) 28 | 29 | Code: [Here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday12072022.ipynb) 30 | 31 | 32 | ## 5 Jul 2022 33 | SF rent and lease distribution. 34 | I tried to do an animation and failed miserably. 35 | I still have to get up to work on Wednesday so I'd try again next week lol. 36 | 37 | 38 | ![image](https://user-images.githubusercontent.com/77285010/177603951-a97a16ef-d9f9-4bf4-8b54-83d9f5414523.png) 39 | 40 | Code: [Here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday05072022.ipynb) 41 | 42 | ## 28 June 2022 43 | UK pay gap. 44 | ![image](https://user-images.githubusercontent.com/77285010/176596978-99360163-e0c4-4cb1-8d6c-5cb0905eb0c2.png) 45 | 46 | Code: [Here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday28062022.ipynb) 47 | 48 | 49 | ## 21 June 2022 50 | In honour of Juneteenth :) did a lot of text processing stuff to brush up my regex. 51 | ![image](https://user-images.githubusercontent.com/77285010/174964887-70fd1b09-d77a-407f-90d9-d83b8b5ee55e.png) 52 | 53 | Code: [Here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday21062022.ipynb) 54 | 55 | ## 14 June 2022 56 | The data set is on droughts in the US but I focused on California in this part. It isn't going well... 57 | ![IMG_6613](https://user-images.githubusercontent.com/77285010/173525177-0d7c189f-62a7-4e32-b12a-fa870e78a982.JPEG) 58 | 59 | Then I also looked into the general trend for every state in the US but this is kind of unclear at first glance... 60 | ![us_droughts](https://user-images.githubusercontent.com/77285010/173766435-c2842e5a-4815-4901-bbb4-e971f3f9c9e6.jpg) 61 | 62 | 63 | Code: [Here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday140622.ipynb) 64 | 65 | ## 7 June 2022 66 | Holding companies donating to anti-LGBTQ politicians accountable. 67 | ![image](https://user-images.githubusercontent.com/77285010/172539932-98749a80-a3f1-42e1-8570-26daa07c6f28.png) 68 | Condensed: 69 | ![image](https://user-images.githubusercontent.com/77285010/172540033-f1fd89da-2932-4224-a0bb-62c658a997ef.png) 70 | 71 | 72 | 73 | Code: [Here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday07062022.ipynb) 74 | 75 | ## 24 May 2022 76 | Women's rugby. 77 | ![image](https://user-images.githubusercontent.com/77285010/172507547-2bd106f1-24d0-430c-83f6-383b9fc0f744.png) 78 | 79 | Code: [Here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday24052022.ipynb) 80 | 81 | ## 17 May 2022 82 | Eurovision! And the drastic contrast between 2022 and 2021. 83 | 84 | 2021: 85 | ![image](https://user-images.githubusercontent.com/77285010/168933051-b9dd7e9a-8796-4dc8-879d-8d03ee2457d5.png) 86 | 87 | Whereas 2022: 88 | ![image](https://user-images.githubusercontent.com/77285010/168933069-18ee2f83-b542-4e1b-99e2-e5cf932eaf88.png) 89 | 90 | All of our best wishes go to Ukraine <3 91 | 92 | Plotted on Python using Basemap in Matplotlib and Geopy. 93 | 94 | Code: [Click here](https://github.com/xh313/TidyTuesdayWithPython/blob/main/TidyTuesday17052022.ipynb) 95 | 96 | ## 3 May 2022 97 | After a month of random COVID disruptions and UCLA DataFest I am finally back to TidyTuesday! 98 | 99 | Today's raw data: https://github.com/rfordatascience/tidytuesday/tree/master/data/2022/2022-05-03 100 | 101 | Graphic: 102 | ![image](https://user-images.githubusercontent.com/77285010/166563044-82c86dd3-f435-4d74-87f8-190df2046339.png) 103 | 104 | 105 | ## 29 Mar 2022 106 | 107 | Plotly is so cool! 108 | 109 | ![ncaafunds](https://user-images.githubusercontent.com/77285010/160757774-009472e4-ab94-4876-93d4-a698e16894c4.png) 110 | 111 | 112 | ## 22 Mar 2022 113 | 114 | Cheesiest plot I've made so far... 115 | - Raw data: [https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-03-22/babynames.csv] 116 | 117 | Graphic: 118 | ![A graphic showing the trendiness of a selection of feminine baby names across the time span from 1960 to 2017.](https://user-images.githubusercontent.com/77285010/159595530-db8cbe5c-5565-4507-8b18-5a7ff6cd0c0e.png) 119 | 120 | XH 121 | 22 Mar 2022 122 | 123 | 124 | ## 08 Mar 2022 125 | 126 | **PENDING** 127 | 128 | 129 | ## 01 Mar 2022 130 | 131 | Tried Geopandas and Geoplots the first time! I'd say I would probably rather use seaborn the next time though... 132 | 133 | Data processing logic: 134 | - Raw data: [https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-03-01/stations.csv] 135 | - Map the points on the country map using the LONGITUDE and LATITUDE columns. 136 | - Colour code the points using the column FUEL_TYPE_CODE distinguishing the fuel types. 137 | 138 | Visual features: 139 | - Designs: 140 | - Map of the US (excluding Alaska and islands) as background with faint county borders 141 | - Translucent data points showing the density of the distribution clearly 142 | - Legend showing fuel types 143 | - Avenir typesetting! Avenir is the best 144 | - Also added Alt text 145 | 146 | Issues: 147 | - Projection: whenever I employ projection methods the session crashes, so now the map looks kind of squished 148 | - The spots on the legend are so faint that it's hard to tell apart the difference in colours 149 | - The legend handles are currently acronym and might work better if I type in the full name 150 | 151 | Plans: 152 | - Maybe fix the projection issue 153 | - Differentiate the colours more 154 | 155 | Graphic: 156 | ![A graphic showing the alternative fuel station distribution in the US. The shape of the country excluding Alaska and islands are shown on the background with bright points indicating the occurrences of the stations in different regions. The colours mark the type of alt fuel the stations supply. ](https://user-images.githubusercontent.com/77285010/156272212-6f779af9-70fd-4352-81c1-7ccfa4a250e0.jpg) 157 | 158 | XH 159 | 01 Mar 2022 160 | 161 | ## 22 Feb 2022 162 | 163 | Happy 22022022 palindrome day! 164 | 165 | *Content note: The raw data given by TidyTuesday this week involves comparison between countries, 166 | which might involve some political disputes and/or underlying assumptions. The raw data does not 167 | come from me and does not represent my political opinions. Please assess the credibility of the 168 | original data under your own judgements.* 169 | 170 | Data processing logic: 171 | - Raw data: [https://github.com/rfordatascience/tidytuesday/blob/master/data/2022/2022-02-22/freedom.csv] 172 | - Selecting the column of 'Status' (Free, partially free and not free) 173 | - Extract the status of each country for every year (1995-2020), count the data and funnel into 3 dictionaries. 174 | - Show the trend of the number of countries that are in each status over the 26 years 175 | 176 | Visual features: 177 | - Designs: 178 | - Used mock-ggplot style with some modifications (facecolor etc.) 179 | - Translucent on-graph legend with sharp corners 180 | - All-filling solid colours with different shades 181 | - Avenir typesetting! Avenir is the best 182 | 183 | Issues: 184 | - Sort of boring (I didn't have much time to make it fancier :( 185 | - Would probably work better if the graph is more horizontal (aka the height could be decreased) 186 | - The grids in the background are useless since the area fills don't have an alpha (quick fix) 187 | 188 | Plans: 189 | - Add alphas to the filled area under curves 190 | - Change graph dimensions 191 | - Improving the documentation and styling 192 | - Alt text 193 | 194 | Graphic: 195 | ![image](https://user-images.githubusercontent.com/77285010/155228929-2977f09b-6437-45b1-88c1-fc0185085030.png) 196 | 197 | XH 198 | 22 Feb 2022 199 | 200 | ## 8 Feb 2022 (actually using the data set from 25 Jan 2022) 201 | I am not interested in random american airforce people so I pulled out an old boardgame data set instead! 202 | 203 | ** LOGGING IN PROCESS NOT FINISHED ** 204 | 205 | Data processing logic: 206 | - Data on dog breeds and their different traits 207 | - Quantifying all qualitative descriptions into scores using text processing 208 | - Weighting and categorising each trait into two new parameters 'friendliness' and 'fluffiness' 209 | - Plot scatter plot with each point corresponding to a breed on the quadrant of fluffiness-friendliness 210 | 211 | Visual features: 212 | - Detecting overlapping points or close-by points automatically and wrap/dodge off the labelling (still bugged :( ) 213 | - Generating a new colour for each data point on the tab 20b palette (or any other palettes, might change it if in the mood) 214 | - Avenir typesetting! Avenir is the best 215 | - Annotation of the breed name beside each data point 216 | - Legend indexing all 190+ breed names 217 | 218 | Issues: 219 | - The overlap detector does not work for certain few points for some reason 220 | - Graph too huge with too many data points -- hard to read! Don't know if there's a better way to present the data! 221 | - Might need to adjust some weighings a bit (as I don't own a dog myself, I am biased!) 222 | 223 | Plans: 224 | - Indexing the position on the diagram for each breed and incorporating into the legend 225 | - Improving the documentation and styling (it is currently unfortunately a mess!) 226 | 227 | Graphic: 228 | ![image](https://user-images.githubusercontent.com/77285010/153077694-223bb4b3-3a34-4551-8f44-0073bddb0e35.png) 229 | 230 | XH 231 | 8 Feb 2022 232 | 233 | ## 1 Feb 2022 234 | 235 | Data processing logic: 236 | - Data on dog breeds and their different traits 237 | - Quantifying all qualitative descriptions into scores using text processing 238 | - Weighting and categorising each trait into two new parameters 'friendliness' and 'fluffiness' 239 | - Plot scatter plot with each point corresponding to a breed on the quadrant of fluffiness-friendliness 240 | 241 | Visual features: 242 | - Detecting overlapping points or close-by points automatically and wrap/dodge off the labelling (still bugged :( ) 243 | - Generating a new colour for each data point on the tab 20b palette (or any other palettes, might change it if in the mood) 244 | - Avenir typesetting! Avenir is the best 245 | - Annotation of the breed name beside each data point 246 | - Legend indexing all 190+ breed names 247 | 248 | Issues: 249 | - The overlap detector does not work for certain few points for some reason 250 | - Graph too huge with too many data points -- hard to read! Don't know if there's a better way to present the data! 251 | - Might need to adjust some weighings a bit (as I don't own a dog myself, I am biased!) 252 | 253 | Plans: 254 | - Indexing the position on the diagram for each breed and incorporating into the legend 255 | - Improving the documentation and styling (it is currently unfortunately a mess!) 256 | 257 | Graphic: 258 | ![graph01022022](https://user-images.githubusercontent.com/77285010/152634365-5ebdee2d-113b-448e-b65c-a557762e87a7.png) 259 | 260 | XH 261 | 5 Feb 2022 262 | -------------------------------------------------------------------------------- /TidyTuesday22022022.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "nbformat": 4, 3 | "nbformat_minor": 0, 4 | "metadata": { 5 | "colab": { 6 | "name": "TidyTuesday22022022.ipynb", 7 | "provenance": [], 8 | "collapsed_sections": [], 9 | "authorship_tag": "ABX9TyOBcLe9cvCuKCaFR2LFrPnV", 10 | "include_colab_link": true 11 | }, 12 | "kernelspec": { 13 | "name": "python3", 14 | "display_name": "Python 3" 15 | }, 16 | "language_info": { 17 | "name": "python" 18 | } 19 | }, 20 | "cells": [ 21 | { 22 | "cell_type": "markdown", 23 | "metadata": { 24 | "id": "view-in-github", 25 | "colab_type": "text" 26 | }, 27 | "source": [ 28 | "\"Open" 29 | ] 30 | }, 31 | { 32 | "cell_type": "code", 33 | "source": [ 34 | "from google.colab import drive\n", 35 | "drive.mount('/content/drive')" 36 | ], 37 | "metadata": { 38 | "colab": { 39 | "base_uri": "https://localhost:8080/" 40 | }, 41 | "id": "S5FH6THp1EFv", 42 | "outputId": "c3d3a209-8270-49d9-fd7e-c49bdf6254e5" 43 | }, 44 | "execution_count": 1, 45 | "outputs": [ 46 | { 47 | "output_type": "stream", 48 | "name": "stdout", 49 | "text": [ 50 | "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n" 51 | ] 52 | } 53 | ] 54 | }, 55 | { 56 | "cell_type": "code", 57 | "execution_count": 2, 58 | "metadata": { 59 | "id": "TEspAZlQ25X7" 60 | }, 61 | "outputs": [], 62 | "source": [ 63 | "import pandas as pd\n", 64 | "import numpy as np\n", 65 | "import matplotlib.pyplot as plt\n", 66 | "import matplotlib.axes as ax\n", 67 | "import matplotlib.pylab as pl\n", 68 | "import math\n", 69 | "from collections import Counter\n", 70 | "import csv\n", 71 | "import matplotlib as mpl\n", 72 | "import matplotlib.style as style" 73 | ] 74 | }, 75 | { 76 | "cell_type": "code", 77 | "source": [ 78 | "all = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-02-22/freedom.csv', skiprows=0)\n", 79 | "df = all\n", 80 | "\n", 81 | "timespan = 26 # years" 82 | ], 83 | "metadata": { 84 | "id": "g62IfFSR61Ou" 85 | }, 86 | "execution_count": 25, 87 | "outputs": [] 88 | }, 89 | { 90 | "cell_type": "code", 91 | "source": [ 92 | "status = list(df['Status'])\n", 93 | "year = list(df['year'])\n", 94 | "\n", 95 | "NFcount = {}\n", 96 | "PFcount = {}\n", 97 | "Fcount = {}\n", 98 | "\n", 99 | "# Initialize the counts\n", 100 | "for i in range(1995, 1995+timespan):\n", 101 | " NFcount[i] = 0\n", 102 | " PFcount[i] = 0\n", 103 | " Fcount[i] = 0\n", 104 | "\n", 105 | "\n", 106 | "# Count the numbers\n", 107 | "for i in range(len(year)):\n", 108 | " if status[i] == 'NF': # NF\n", 109 | " NFcount[year[i]] += 1\n", 110 | " if status[i] == 'F': # F\n", 111 | " Fcount[year[i]] += 1\n", 112 | " else:\n", 113 | " PFcount[year[i]] += 1\n", 114 | "\n", 115 | "print(Fcount)" 116 | ], 117 | "metadata": { 118 | "colab": { 119 | "base_uri": "https://localhost:8080/" 120 | }, 121 | "id": "X3RStKDh85E3", 122 | "outputId": "4c3033e5-8e8b-41b1-e908-66012978be68" 123 | }, 124 | "execution_count": 4, 125 | "outputs": [ 126 | { 127 | "output_type": "stream", 128 | "name": "stdout", 129 | "text": [ 130 | "{1995: 76, 1996: 78, 1997: 80, 1998: 86, 1999: 84, 2000: 85, 2001: 84, 2002: 87, 2003: 87, 2004: 88, 2005: 88, 2006: 89, 2007: 89, 2008: 88, 2009: 88, 2010: 86, 2011: 86, 2012: 89, 2013: 87, 2014: 88, 2015: 85, 2016: 86, 2017: 87, 2018: 85, 2019: 82, 2020: 81}\n" 131 | ] 132 | } 133 | ] 134 | }, 135 | { 136 | "cell_type": "code", 137 | "source": [ 138 | "# Styling\n", 139 | "\n", 140 | "style.use('seaborn-talk')\n", 141 | "style.use('ggplot')\n", 142 | "\n", 143 | "mpl.font_manager.fontManager.addfont('/content/drive/MyDrive/Avenir.ttc')\n", 144 | "mpl.rc('font', family='Avenir') # Changing all runtime fonts into Avenir" 145 | ], 146 | "metadata": { 147 | "id": "GgDpku4mKtXl" 148 | }, 149 | "execution_count": 22, 150 | "outputs": [] 151 | }, 152 | { 153 | "cell_type": "code", 154 | "source": [ 155 | "# Variables\n", 156 | "nf = list(NFcount.values())\n", 157 | "pf = list(PFcount.values())\n", 158 | "f = list(Fcount.values())\n", 159 | "\n", 160 | "time = np.linspace(1995, 2021, timespan)\n", 161 | "\n", 162 | "plt.figure(dpi = 80, facecolor='#e5e5e5')\n", 163 | "#plt.plot(time, f, '-')\n", 164 | "plt.fill_between(time, pf, label='Partially Free', color='#8bb7d2')\n", 165 | "plt.fill_between(time, f, label='Free', color='#448ab5')\n", 166 | "plt.fill_between(time, nf, label='Not Free', color='#396581')\n", 167 | "\n", 168 | "plt.ylabel('Number of Countries')#, fontdict={'size':10})\n", 169 | "plt.xlabel('Years')#, fontdict={'size':10})\n", 170 | "plt.xlim((1995,2020))\n", 171 | "plt.ylim(bottom=0)\n", 172 | "plt.title('Freedom in the World Over the Years')\n", 173 | "\n", 174 | "plt.legend(bbox_to_anchor=(0.1, 0.05, 0.8, .102), loc='center',\n", 175 | " ncol=3, mode=\"expand\", borderaxespad=0., fancybox=False)\n", 176 | "plt.show()" 177 | ], 178 | "metadata": { 179 | "colab": { 180 | "base_uri": "https://localhost:8080/", 181 | "height": 529 182 | }, 183 | "id": "inBMAElhGy2E", 184 | "outputId": "c9539e1a-896a-4bac-bb64-12c31609ea48" 185 | }, 186 | "execution_count": 24, 187 | "outputs": [ 188 | { 189 | "output_type": "display_data", 190 | "data": { 191 | "image/png": "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\n", 192 | "text/plain": [ 193 | "
" 194 | ] 195 | }, 196 | "metadata": {} 197 | } 198 | ] 199 | } 200 | ] 201 | } -------------------------------------------------------------------------------- /TidyTuesday29032022.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "nbformat": 4, 3 | "nbformat_minor": 0, 4 | "metadata": { 5 | "colab": { 6 | "name": "TidyTuesday29032022.ipynb", 7 | "provenance": [], 8 | "authorship_tag": "ABX9TyNS4By/R1Cey+pp+6U7OtS8", 9 | "include_colab_link": true 10 | }, 11 | "kernelspec": { 12 | "name": "python3", 13 | "display_name": "Python 3" 14 | }, 15 | "language_info": { 16 | "name": "python" 17 | } 18 | }, 19 | "cells": [ 20 | { 21 | "cell_type": "markdown", 22 | "metadata": { 23 | "id": "view-in-github", 24 | "colab_type": "text" 25 | }, 26 | "source": [ 27 | "\"Open" 28 | ] 29 | }, 30 | { 31 | "cell_type": "code", 32 | "execution_count": null, 33 | "metadata": { 34 | "id": "B1SMxs7F8Wum" 35 | }, 36 | "outputs": [], 37 | "source": [ 38 | "" 39 | ] 40 | }, 41 | { 42 | "cell_type": "code", 43 | "execution_count": 1, 44 | "metadata": { 45 | "id": "uqmmCeFGFGP-" 46 | }, 47 | "outputs": [], 48 | "source": [ 49 | "# Run from here after first time\n", 50 | "import pandas as pd\n", 51 | "import numpy as np\n", 52 | "import matplotlib.pyplot as plt\n", 53 | "import matplotlib.axes as ax\n", 54 | "import matplotlib.pylab as pl\n", 55 | "import math\n", 56 | "from collections import Counter\n", 57 | "import csv\n", 58 | "import matplotlib as mpl\n", 59 | "import seaborn as sns" 60 | ] 61 | }, 62 | { 63 | "cell_type": "code", 64 | "source": [ 65 | "all = pd.read_csv('https://raw.githubusercontent.com/rfordatascience\\\n", 66 | "/tidytuesday/master/data/2022/2022-03-29/sports.csv', low_memory=False)\n", 67 | "\n", 68 | "all['gender'] = all['sum_partic_men'] > all['sum_partic_women']\n", 69 | "\n", 70 | "list_sports = ['Basketball', 'Football', 'Golf', 'Baseball', \n", 71 | " 'Volleyball', 'Swimming', 'Wrestling', 'Softball']\n", 72 | "\n", 73 | "df = all[all.sports.isin(list_sports) & (all['total_exp_menwomen'] < 1000000)\\\n", 74 | " & (all['total_exp_menwomen'] > 100000)] # Filter out abnormal data\n", 75 | "df.describe()" 76 | ], 77 | "metadata": { 78 | "colab": { 79 | "base_uri": "https://localhost:8080/", 80 | "height": 394 81 | }, 82 | "id": "Clbbk33J9dX_", 83 | "outputId": "cb702404-e6c1-4b66-c330-0afd536a43e5" 84 | }, 85 | "execution_count": 89, 86 | "outputs": [ 87 | { 88 | "output_type": "execute_result", 89 | "data": { 90 | "text/plain": [ 91 | " year unitid zip_text classification_code \\\n", 92 | "count 30535.000000 30535.000000 3.050700e+04 30535.000000 \n", 93 | "mean 2017.009170 183153.928476 6.151950e+07 7.337416 \n", 94 | "std 1.408475 56986.722425 1.873143e+08 3.987694 \n", 95 | "min 2015.000000 100654.000000 6.810000e+02 1.000000 \n", 96 | "25% 2016.000000 148496.000000 2.963900e+04 4.000000 \n", 97 | "50% 2017.000000 179043.000000 5.320200e+04 6.000000 \n", 98 | "75% 2018.000000 213598.000000 8.105000e+04 10.000000 \n", 99 | "max 2019.000000 800001.000000 9.977575e+08 20.000000 \n", 100 | "\n", 101 | " ef_male_count ef_female_count ef_total_count sector_cd \\\n", 102 | "count 30535.000000 30535.000000 30535.000000 30535.000000 \n", 103 | "mean 1616.054560 1972.100835 3588.155395 2.179532 \n", 104 | "std 1923.261546 2288.410532 4153.982485 3.103907 \n", 105 | "min 0.000000 0.000000 0.000000 1.000000 \n", 106 | "25% 514.000000 629.000000 1173.000000 1.000000 \n", 107 | "50% 894.000000 1139.000000 2062.000000 2.000000 \n", 108 | "75% 1951.500000 2443.000000 4389.500000 2.000000 \n", 109 | "max 17376.000000 25361.000000 36401.000000 99.000000 \n", 110 | "\n", 111 | " sportscode partic_men ... partic_coed_men partic_coed_women \\\n", 112 | "count 30535.000000 19844.000000 ... 0.0 0.0 \n", 113 | "mean 11.194334 30.791373 ... NaN NaN \n", 114 | "std 9.757280 26.348312 ... NaN NaN \n", 115 | "min 1.000000 1.000000 ... NaN NaN \n", 116 | "25% 2.000000 14.000000 ... NaN NaN \n", 117 | "50% 8.000000 22.000000 ... NaN NaN \n", 118 | "75% 16.000000 36.000000 ... NaN NaN \n", 119 | "max 28.000000 251.000000 ... NaN NaN \n", 120 | "\n", 121 | " sum_partic_men sum_partic_women rev_men rev_women \\\n", 122 | "count 30535.000000 30535.000000 1.984400e+04 2.090400e+04 \n", 123 | "mean 20.010611 11.060062 2.835943e+05 2.551100e+05 \n", 124 | "std 25.824316 9.135903 2.097301e+05 1.889236e+05 \n", 125 | "min 0.000000 0.000000 1.253000e+03 1.177000e+03 \n", 126 | "25% 0.000000 0.000000 1.320480e+05 1.226078e+05 \n", 127 | "50% 14.000000 13.000000 2.167260e+05 1.957325e+05 \n", 128 | "75% 30.000000 18.000000 3.862922e+05 3.349522e+05 \n", 129 | "max 251.000000 121.000000 3.460784e+06 4.064427e+06 \n", 130 | "\n", 131 | " total_rev_menwomen exp_men exp_women total_exp_menwomen \n", 132 | "count 3.053500e+04 19844.000000 20904.000000 30535.000000 \n", 133 | "mean 3.589476e+05 278618.552056 253752.817403 354784.851547 \n", 134 | "std 2.335386e+05 200018.096784 187098.457932 226116.131079 \n", 135 | "min 1.177000e+03 12950.000000 13623.000000 100001.000000 \n", 136 | "25% 1.735285e+05 129725.500000 120893.500000 171083.000000 \n", 137 | "50% 2.893730e+05 213711.000000 193643.000000 286411.000000 \n", 138 | "75% 4.827165e+05 382003.250000 332744.750000 479724.500000 \n", 139 | "max 4.064427e+06 999899.000000 999948.000000 999948.000000 \n", 140 | "\n", 141 | "[8 rows x 21 columns]" 142 | ], 143 | "text/html": [ 144 | "\n", 145 | "
\n", 146 | "
\n", 147 | "
\n", 148 | "\n", 161 | "\n", 162 | " \n", 163 | " \n", 164 | " \n", 165 | " \n", 166 | " \n", 167 | " \n", 168 | " \n", 169 | " \n", 170 | " \n", 171 | " \n", 172 | " \n", 173 | " \n", 174 | " \n", 175 | " \n", 176 | " \n", 177 | " \n", 178 | " \n", 179 | " \n", 180 | " \n", 181 | " \n", 182 | " \n", 183 | " \n", 184 | " \n", 185 | " \n", 186 | " \n", 187 | " \n", 188 | " \n", 189 | " \n", 190 | " \n", 191 | " \n", 192 | " \n", 193 | " \n", 194 | " \n", 195 | " \n", 196 | " \n", 197 | " \n", 198 | " \n", 199 | " \n", 200 | " \n", 201 | " \n", 202 | " \n", 203 | " \n", 204 | " \n", 205 | " \n", 206 | " \n", 207 | " \n", 208 | " \n", 209 | " \n", 210 | " \n", 211 | " \n", 212 | " \n", 213 | " \n", 214 | " \n", 215 | " \n", 216 | " \n", 217 | " \n", 218 | " \n", 219 | " \n", 220 | " \n", 221 | " \n", 222 | " \n", 223 | " \n", 224 | " \n", 225 | " \n", 226 | " \n", 227 | " \n", 228 | " \n", 229 | " \n", 230 | " \n", 231 | " \n", 232 | " \n", 233 | " \n", 234 | " \n", 235 | " \n", 236 | " \n", 237 | " \n", 238 | " \n", 239 | " \n", 240 | " \n", 241 | " \n", 242 | " \n", 243 | " \n", 244 | " \n", 245 | " \n", 246 | " \n", 247 | " \n", 248 | " \n", 249 | " \n", 250 | " \n", 251 | " \n", 252 | " \n", 253 | " \n", 254 | " \n", 255 | " \n", 256 | " \n", 257 | " \n", 258 | " \n", 259 | " \n", 260 | " \n", 261 | " \n", 262 | " \n", 263 | " \n", 264 | " \n", 265 | " \n", 266 | " \n", 267 | " \n", 268 | " \n", 269 | " \n", 270 | " \n", 271 | " \n", 272 | " \n", 273 | " \n", 274 | " \n", 275 | " \n", 276 | " \n", 277 | " \n", 278 | " \n", 279 | " \n", 280 | " \n", 281 | " \n", 282 | " \n", 283 | " \n", 284 | " \n", 285 | " \n", 286 | " \n", 287 | " \n", 288 | " \n", 289 | " \n", 290 | " \n", 291 | " \n", 292 | " \n", 293 | " \n", 294 | " \n", 295 | " \n", 296 | " \n", 297 | " \n", 298 | " \n", 299 | " \n", 300 | " \n", 301 | " \n", 302 | " \n", 303 | " \n", 304 | " \n", 305 | " \n", 306 | " \n", 307 | " \n", 308 | " \n", 309 | " \n", 310 | " \n", 311 | " \n", 312 | " \n", 313 | " \n", 314 | " \n", 315 | " \n", 316 | " \n", 317 | " \n", 318 | " \n", 319 | " \n", 320 | " \n", 321 | " \n", 322 | " \n", 323 | " \n", 324 | " \n", 325 | " \n", 326 | " \n", 327 | " \n", 328 | " \n", 329 | " \n", 330 | " \n", 331 | " \n", 332 | " \n", 333 | " \n", 334 | " \n", 335 | " \n", 336 | " \n", 337 | " \n", 338 | " \n", 339 | " \n", 340 | " \n", 341 | " \n", 342 | " \n", 343 | " \n", 344 | " \n", 345 | " \n", 346 | " \n", 347 | " \n", 348 | " \n", 349 | " \n", 350 | " \n", 351 | " \n", 352 | " \n", 353 | " \n", 354 | " \n", 355 | " \n", 356 | " \n", 357 | " \n", 358 | " \n", 359 | " \n", 360 | " \n", 361 | " \n", 362 | " \n", 363 | " \n", 364 | " \n", 365 | " \n", 366 | " \n", 367 | " \n", 368 | " \n", 369 | " \n", 370 | " \n", 371 | " \n", 372 | " \n", 373 | " \n", 374 | " \n", 375 | " \n", 376 | " \n", 377 | " \n", 378 | " \n", 379 | " \n", 380 | " \n", 381 | " \n", 382 | "
yearunitidzip_textclassification_codeef_male_countef_female_countef_total_countsector_cdsportscodepartic_men...partic_coed_menpartic_coed_womensum_partic_mensum_partic_womenrev_menrev_womentotal_rev_menwomenexp_menexp_womentotal_exp_menwomen
count30535.00000030535.0000003.050700e+0430535.00000030535.00000030535.00000030535.00000030535.00000030535.00000019844.000000...0.00.030535.00000030535.0000001.984400e+042.090400e+043.053500e+0419844.00000020904.00000030535.000000
mean2017.009170183153.9284766.151950e+077.3374161616.0545601972.1008353588.1553952.17953211.19433430.791373...NaNNaN20.01061111.0600622.835943e+052.551100e+053.589476e+05278618.552056253752.817403354784.851547
std1.40847556986.7224251.873143e+083.9876941923.2615462288.4105324153.9824853.1039079.75728026.348312...NaNNaN25.8243169.1359032.097301e+051.889236e+052.335386e+05200018.096784187098.457932226116.131079
min2015.000000100654.0000006.810000e+021.0000000.0000000.0000000.0000001.0000001.0000001.000000...NaNNaN0.0000000.0000001.253000e+031.177000e+031.177000e+0312950.00000013623.000000100001.000000
25%2016.000000148496.0000002.963900e+044.000000514.000000629.0000001173.0000001.0000002.00000014.000000...NaNNaN0.0000000.0000001.320480e+051.226078e+051.735285e+05129725.500000120893.500000171083.000000
50%2017.000000179043.0000005.320200e+046.000000894.0000001139.0000002062.0000002.0000008.00000022.000000...NaNNaN14.00000013.0000002.167260e+051.957325e+052.893730e+05213711.000000193643.000000286411.000000
75%2018.000000213598.0000008.105000e+0410.0000001951.5000002443.0000004389.5000002.00000016.00000036.000000...NaNNaN30.00000018.0000003.862922e+053.349522e+054.827165e+05382003.250000332744.750000479724.500000
max2019.000000800001.0000009.977575e+0820.00000017376.00000025361.00000036401.00000099.00000028.000000251.000000...NaNNaN251.000000121.0000003.460784e+064.064427e+064.064427e+06999899.000000999948.000000999948.000000
\n", 383 | "

8 rows × 21 columns

\n", 384 | "
\n", 385 | " \n", 395 | " \n", 396 | " \n", 433 | "\n", 434 | " \n", 458 | "
\n", 459 | "
\n", 460 | " " 461 | ] 462 | }, 463 | "metadata": {}, 464 | "execution_count": 89 465 | } 466 | ] 467 | }, 468 | { 469 | "cell_type": "code", 470 | "source": [ 471 | "# Using pandas methods and slicing to determine the order by decreasing median\n", 472 | "my_order = df.groupby(by=[\"sports\"])[\"total_exp_menwomen\"].median().iloc[::-1].index" 473 | ], 474 | "metadata": { 475 | "id": "4r2SetFkgpPz" 476 | }, 477 | "execution_count": 85, 478 | "outputs": [] 479 | }, 480 | { 481 | "cell_type": "code", 482 | "source": [ 483 | "# Version using plotly\n", 484 | "\n", 485 | "import plotly.graph_objects as go\n", 486 | "\n", 487 | "fig = go.Figure()\n", 488 | "\n", 489 | "fig.add_trace(go.Violin(x=df['sports'][df['sum_partic_men'] < df['sum_partic_women']],\n", 490 | " y=df['total_exp_menwomen'][df['sum_partic_men'] < df['sum_partic_women']],\n", 491 | " legendgroup='Women Dominated', scalegroup='Women Dominated', name='Women Dominated',\n", 492 | " side='negative', marker=None, points=None,\n", 493 | " line_color='royalblue')\n", 494 | " )\n", 495 | "fig.add_trace(go.Violin(x=df['sports'][df['sum_partic_men'] >= df['sum_partic_women']],\n", 496 | " y=df['total_exp_menwomen'][df['sum_partic_men'] >= df['sum_partic_women']],\n", 497 | " legendgroup='Men Dominated', scalegroup='Men Dominated', name='Men Dominated',\n", 498 | " side='positive', marker=None, points=None,\n", 499 | " line_color='lightseagreen')\n", 500 | " )\n", 501 | "fig.update_traces(meanline_visible=True,)\n", 502 | "fig.update_layout(violingap=0, violinmode='overlay',\n", 503 | " title_text='Annual expenditure in Men- vs Women-Dominated Collegiate Sports', \n", 504 | " #showlegend=False\n", 505 | " )\n", 506 | "fig.show()" 507 | ], 508 | "metadata": { 509 | "id": "Z7C-7WJv2Ni6" 510 | }, 511 | "execution_count": null, 512 | "outputs": [] 513 | }, 514 | { 515 | "cell_type": "markdown", 516 | "source": [ 517 | "![ncaafunds](https://user-images.githubusercontent.com/77285010/160757774-009472e4-ab94-4876-93d4-a698e16894c4.png)" 518 | ], 519 | "metadata": { 520 | "id": "xDt2Z8_MTePZ" 521 | } 522 | }, 523 | { 524 | "cell_type": "code", 525 | "source": [ 526 | "# Normal seaborn plot\n", 527 | "sns.set_theme(style=\"whitegrid\")\n", 528 | "\n", 529 | "ax = sns.violinplot(data=df, x=\"sports\", y=\"total_exp_menwomen\", hue=\"gender\",\n", 530 | " split=True, inner=\"quart\", linewidth=1, order=my_order,\n", 531 | " palette='Set2')\n", 532 | "\n", 533 | "sns.despine(left=True)\n", 534 | "\n", 535 | "plt.show()" 536 | ], 537 | "metadata": { 538 | "colab": { 539 | "base_uri": "https://localhost:8080/", 540 | "height": 296 541 | }, 542 | "id": "ufIH09dDgGOd", 543 | "outputId": "a8e800e9-fbe0-4eb4-8c20-f71e9861c692" 544 | }, 545 | "execution_count": 90, 546 | "outputs": [ 547 | { 548 | "output_type": "display_data", 549 | "data": { 550 | "text/plain": [ 551 | "
" 552 | ], 553 | "image/png": "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\n" 554 | }, 555 | "metadata": {} 556 | } 557 | ] 558 | }, 559 | { 560 | "cell_type": "code", 561 | "source": [ 562 | "fig.write_html(\"ncaafunds.html\")" 563 | ], 564 | "metadata": { 565 | "id": "UP2Yq23JDMbC" 566 | }, 567 | "execution_count": 103, 568 | "outputs": [] 569 | } 570 | ] 571 | } --------------------------------------------------------------------------------