diff --git a/Topic_03_Presentation/universities-intake-enrolment-and-graduates-by-course.ipynb b/Topic_03_Presentation/universities-intake-enrolment-and-graduates-by-course.ipynb index 1e08f326f7d13771fd5d4aac54b1ee6f296a89c5..074e36c48ea40aab9d9a689043739a2789d5bc55 100644 --- a/Topic_03_Presentation/universities-intake-enrolment-and-graduates-by-course.ipynb +++ b/Topic_03_Presentation/universities-intake-enrolment-and-graduates-by-course.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -47,8 +47,10 @@ }, { "cell_type": "code", - "execution_count": 2, - "metadata": {}, + "execution_count": 3, + "metadata": { + "scrolled": false + }, "outputs": [ { "data": { @@ -84,30 +86,201 @@ " ax[x, 1].legend(loc=\"lower right\") \r\n", " x += 1" ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3.9.4 64-bit", - "name": "python394jvsc74a57bd0ac59ebe37160ed0dfa835113d9b8498d9f09ceb179beaac4002f036b9467c963" }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Describing the data" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "scrolled": true + }, + "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
yearsexcourseintakeenrolmentgraduates
count330330330330330330
unique11215268306265
top2009FHumanities & Social Sciences000
freq3016522444
\n
", + "text/plain": " year sex course intake enrolment graduates\ncount 330 330 330 330 330 330\nunique 11 2 15 268 306 265\ntop 2009 F Humanities & Social Sciences 0 0 0\nfreq 30 165 22 4 4 4" + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#using describe function to get various summary statistics that exclude NaN values.\n", + "data_course_year_final.describe()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 330 entries, 0 to 329\n", + "Data columns (total 6 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 year 330 non-null object\n", + " 1 sex 330 non-null object\n", + " 2 course 330 non-null object\n", + " 3 intake 330 non-null object\n", + " 4 enrolment 330 non-null object\n", + " 5 graduates 330 non-null object\n", + "dtypes: object(6)\n", + "memory usage: 15.6+ KB\n" + ] + } + ], + "source": [ + "data_course_year_final.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": "(450, 6)" + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "numerical = [\n", + " 'intake','enrolment','graduates'\n", + "]\n", + "categorical = [\n", + " 'year','sex','course'\n", + "]\n", + "\n", + "course_data = data_raw[numerical + categorical]\n", + "course_data.shape" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "From above data describe function, we can have a simple bird's eye view on our extracted data table on the possiblities on our data analysis and the basic sanity of the dataset.\n", + "I.E we can see the unique value for column 'Sex' is 2 which is correct across the whole dataset as it should only consist of M & F" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Correlation\n", + "With respect to real-world datasets, there may be overloading amount of elements to analyze which may increase the complexity to the purpose of the project. Hence there we will need single out certain features to further scrutinize for more meaningful analysis. We can take a look at methods such as correlations to filter out more features we may want to pay more attention to." + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "scrolled": true }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.9.4" + "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": [ + "import seaborn as sns\n", + "import numpy as np\n", + "\n", + "#splitting out the numerical values segment of the dataset to run correlation analysis\n", + "selected_values = ['intake','enrolment','graduates']\n", + "data_selected = data_course_year_final[selected_values].values\n", + "data_frame = pd.DataFrame(data_selected , columns = selected_values)\n", + "data_frame['intake'] = pd.to_numeric(data_frame['intake'],downcast=\"float\")\n", + "data_frame['enrolment'] = pd.to_numeric(data_frame['enrolment'],downcast=\"float\")\n", + "data_frame['graduates'] = pd.to_numeric(data_frame['graduates'],downcast=\"float\")\n", + "#conversion of the dataset to float\n", + "\n", + "corr=data_frame.corr()\n", + "\n", + "f, ax = plt.subplots(figsize=(10, 8))\n", + "data_corr = data_frame.corr()\n", + "sns.heatmap(data_corr,\n", + " xticklabels=data_corr.columns.values,\n", + " yticklabels=data_corr.columns.values)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Albeit simple, we can see from the heatmap that all of the above 3x3 features are highly correlated. However, scale-wise, we can see that enrolment does not directly correlate to graduation and in the same fashion, intake does not directly mean admission(enrolment)." + ] }, - "metadata": { - "interpreter": { - "hash": "ac59ebe37160ed0dfa835113d9b8498d9f09ceb179beaac4002f036b9467c963" - } + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Analyzing numerical against categorical variables." + ] }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": "
" + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plt.figure(figsize=(12,10))\n", + "sns.barplot(x=course_data['course'], y=data_frame['graduates'],palette=sns.cubehelix_palette(len(course_data['course'])))\n", + "# Place the region names at a 90-degree angle.\n", + "plt.xticks(rotation= 90)\n", + "plt.xlabel('Course')\n", + "plt.ylabel('Graduates')\n", + "plt.title('Course Vs Graduation')\n", + "plt.show()" + ] + } + ], + "metadata": { + "language_info": {}, "orig_nbformat": 3 }, "nbformat": 4,