2024-heraklion-data/notebooks/030_tabular_data/011_pandas_introduction_tutor.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8cc1c960",
   "metadata": {},
   "source": [
    "# Pandas, quick introduction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "0f55dab1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4b377c42",
   "metadata": {},
   "source": [
    "# Pandas introduces a tabular data structure, the DataFrame\n",
    "\n",
    "* Columns can be of any C-native type\n",
    "* Columns and rows have indices, i.e. labels that identify each column or row"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ec75edbe",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(\n",
    "    data = [\n",
    "        ['Anthony', 28, 1.53], \n",
    "        ['Maria', 31, 1.76], \n",
    "        ['Emma', 26, 1.83], \n",
    "        ['Philip', 41, 1.81], \n",
    "        ['Bill', 27, None],\n",
    "    ],\n",
    "    columns = ['name', 'age', 'height'],\n",
    "    index=['A484', 'C012', 'A123', 'B663', 'A377'],\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "37318480",
   "metadata": {},
   "outputs": [],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fe1c5739",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dedad6f3",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "e31f21c6",
   "metadata": {},
   "source": [
    "## DataFrame attributes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4109f1eb",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "708f9bb5",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "cb2f33b9",
   "metadata": {},
   "source": [
    "## Indexing rows and columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "19ef2738",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8f354ffc",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "94563f03",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "43ab5233",
   "metadata": {},
   "source": [
    "## Examining a column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f2cb544c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "86388f86",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "fc081b90",
   "metadata": {},
   "source": [
    "# Filtering"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "263ae06c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "318da062",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "a570023a",
   "metadata": {},
   "source": [
    "# Basic operations are by column (unlike NumPy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7260d212",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "49b7057a",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f5a0f053",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7e1ffe32",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "7cf9b5d7",
   "metadata": {},
   "source": [
    "# Operations on strings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b78bc237",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0236069f",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5761725b",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ce3d54ad",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "8c5584db",
   "metadata": {},
   "source": [
    "# Adding new columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f6e09176",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f9a552f0",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2e354ace",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}