{ "cells": [ { "cell_type": "markdown", "id": "43e3cce0", "metadata": {}, "source": [ "# Application Session 2\n", "## Descriptive Statistics with NumPy & Pandas (Google Colab)\n", "\n", "**Session goals:**\n", "- Compute descriptive statistics for numerical data (location and spread)\n", "- Use **NumPy** functions alongside Pandas\n", "\n", "**Alignment note:** Application Session 2 implements the descriptive statistics of data (location and spread) introduced in Unit 1, using Python (NumPy and Pandas libraries).\n", "\n", "---" ] }, { "cell_type": "markdown", "id": "63027af7", "metadata": {}, "source": [ "### Step 1: Import required libraries\n", "\n", "- **Pandas (`pandas`)**: for loading and organizing tabular data (covered in session 1)\n", "- **NumPy (`numpy`)**: a widely used Python library that helps work with numbers and perform statistical and mathematical calculations. It is commonly used in many applications such as data analysis, engineering, and scientific computing." ] }, { "cell_type": "code", "execution_count": 1, "id": "1e5ec9a4", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd" ] }, { "cell_type": "markdown", "id": "a9bf1f26", "metadata": {}, "source": [ "### Step 2: Load the dataset\n", "\n", "We use the same dataset of **11 students** introduced in Session 1.\n", "The dataset contains study hours and assessment results." ] }, { "cell_type": "code", "execution_count": 2, "id": "b34e8525", "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", "
student_idgenderhours_studiedquiz1quiz2scoredate
0S01M0.532.0492026-01-15
1S02M2.067.0652026-01-18
2S03F3.077.0702026-01-18
3S04M3.078.0722026-01-19
4S05F4.08NaN752026-01-19
5S06M4.089.0782026-01-20
6S07F5.099.0802026-01-20
7S08M5.0910.0822026-01-21
8S09F6.01010.0852026-01-21
9S10M7.01010.0882026-01-22
10S11F8.01010.0902026-01-22
\n", "
" ], "text/plain": [ " student_id gender hours_studied quiz1 quiz2 score date\n", "0 S01 M 0.5 3 2.0 49 2026-01-15\n", "1 S02 M 2.0 6 7.0 65 2026-01-18\n", "2 S03 F 3.0 7 7.0 70 2026-01-18\n", "3 S04 M 3.0 7 8.0 72 2026-01-19\n", "4 S05 F 4.0 8 NaN 75 2026-01-19\n", "5 S06 M 4.0 8 9.0 78 2026-01-20\n", "6 S07 F 5.0 9 9.0 80 2026-01-20\n", "7 S08 M 5.0 9 10.0 82 2026-01-21\n", "8 S09 F 6.0 10 10.0 85 2026-01-21\n", "9 S10 M 7.0 10 10.0 88 2026-01-22\n", "10 S11 F 8.0 10 10.0 90 2026-01-22" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "csv_text = \"\"\"student_id,gender,hours_studied,quiz1,quiz2,score,date\n", "S01,M,0.5,3,2,49,2026-01-15\n", "S02,M,2,6,7,65,2026-01-18\n", "S03,F,3,7,7,70,2026-01-18\n", "S04,M,3,7,8,72,2026-01-19\n", "S05,F,4,8,,75,2026-01-19\n", "S06,M,4,8,9,78,2026-01-20\n", "S07,F,5,9,9,80,2026-01-20\n", "S08,M,5,9,10,82,2026-01-21\n", "S09,F,6,10,10,85,2026-01-21\n", "S10,M,7,10,10,88,2026-01-22\n", "S11,F,8,10,10,90,2026-01-22\n", "\"\"\"\n", "with open(\"students.csv\", \"w\") as f:\n", " f.write(csv_text)\n", "\n", "df = pd.read_csv(\"students.csv\")\n", "df" ] }, { "cell_type": "markdown", "id": "2bcd5e0c", "metadata": {}, "source": [ "### Step 3: Descriptive statistics using Pandas\n", "\n", "Generate descriptive statistics using Pandas methods." ] }, { "cell_type": "code", "execution_count": 3, "id": "f49e89f5", "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", "
hours_studiedquiz1quiz2score
count11.00000011.00000010.00000011.000000
mean4.3181827.9090918.20000075.818182
std2.1940002.1191772.48551411.745792
min0.5000003.0000002.00000049.000000
25%3.0000007.0000007.25000071.000000
50%4.0000008.0000009.00000078.000000
75%5.5000009.50000010.00000083.500000
max8.00000010.00000010.00000090.000000
\n", "
" ], "text/plain": [ " hours_studied quiz1 quiz2 score\n", "count 11.000000 11.000000 10.000000 11.000000\n", "mean 4.318182 7.909091 8.200000 75.818182\n", "std 2.194000 2.119177 2.485514 11.745792\n", "min 0.500000 3.000000 2.000000 49.000000\n", "25% 3.000000 7.000000 7.250000 71.000000\n", "50% 4.000000 8.000000 9.000000 78.000000\n", "75% 5.500000 9.500000 10.000000 83.500000\n", "max 8.000000 10.000000 10.000000 90.000000" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Descriptive statistics for numerical variables (inspection only)\n", "df[['hours_studied', 'quiz1', 'quiz2', 'score']].describe()" ] }, { "cell_type": "markdown", "id": "8f6e9f7e", "metadata": {}, "source": [ "### Step 4: Descriptive statistics using NumPy\n", "\n", "Now we compute the same statistics using NumPy to show how numerical libraries work together. NumPy works with arrays of numbers and is used to perform fast numerical and statistical calculations.\n" ] }, { "cell_type": "code", "execution_count": 4, "id": "246c3b05", "metadata": {}, "outputs": [], "source": [ "# Convert Pandas Series to NumPy arrays\n", "scores = df['score'].to_numpy()\n", "hours = df['hours_studied'].to_numpy()" ] }, { "cell_type": "code", "execution_count": 5, "id": "ba42e926", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "75.81818181818181 78.0\n" ] } ], "source": [ "# Central tendency using NumPy\n", "x_par= np.mean(scores)\n", "m= np.median(scores)\n", "\n", "print(x_par,m)" ] }, { "cell_type": "code", "execution_count": 6, "id": "270395fe", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "11.74579228335136\n" ] } ], "source": [ "# Spread using NumPy (ddof = 1 → sample standard deviation , ddof = 0 → population standard deviation)\n", "std=np.std(scores, ddof=1)\n", "print(std)" ] }, { "cell_type": "code", "execution_count": 7, "id": "0621d88e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "49 90\n" ] } ], "source": [ "# Minimum and maximum values\n", "min= np.min(scores)\n", "max= np.max(scores)\n", "\n", "print(min,max)" ] }, { "cell_type": "code", "execution_count": 8, "id": "4620c124", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "71.0 78.0 83.5\n" ] } ], "source": [ "# Compute the first, second (median), and third quartiles (25th, 50th, and 75th percentiles)\n", "q1=np.percentile(scores, 25)\n", "q2=np.percentile(scores, 50)\n", "q3=np.percentile(scores, 75)\n", "print(q1,q2,q3)" ] }, { "cell_type": "markdown", "id": "bbfd32f9", "metadata": {}, "source": [ "### Step 5: Additional Descriptive Measures (Unit 1 completion)\n", "\n", "\n", "Compute additional descriptive measures to extend the analysis. The following measures are included to cover the numerical summaries introduced in Unit 1." ] }, { "cell_type": "code", "execution_count": 9, "id": "d093418a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "41\n" ] } ], "source": [ "# Range of scores\n", "score_range = np.max(scores) - np.min(scores)\n", "print(score_range)" ] }, { "cell_type": "code", "execution_count": 10, "id": "8ca474c2", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 3.0\n", "1 4.0\n", "2 5.0\n", "dtype: float64" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Mode (most frequent value), NumPy does not provide a direct mode function.\n", "df['hours_studied'].mode()" ] }, { "cell_type": "code", "execution_count": 11, "id": "25aeae6a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "137.96363636363634\n" ] } ], "source": [ "# Variance (ddof = 1 → sample variance , ddof = 0 → population variance)\n", "var= np.var(scores, ddof=1)\n", "print(var)" ] }, { "cell_type": "code", "execution_count": 12, "id": "b7b2bea8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "12.5\n" ] } ], "source": [ "# Interquartile Range (IQR = Q3 - Q1)\n", "iqr = q3 - q1\n", "print(iqr)" ] }, { "cell_type": "markdown", "id": "b0ded929", "metadata": {}, "source": [ "---\n", "### End of Session 2\n", "**Note:**\n", "- This session implemented main numerical summary measures (location and spread) from Unit 1 using Pandas and NumPy.\n", "- Measures covered include mean, median, mode, variance, standard deviation, range, and IQR.\n", "- In Session 3, we will visualize the data using graphs.\n" ] } ], "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": "3.10.6" } }, "nbformat": 4, "nbformat_minor": 5 }