strings and text

strings manipulation.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Define a text for the examples\nword = \"Hello world\"",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Extract characters based on position (first position = 0)\nprint(word[2:5])  # From Ath to Bth char\nprint(word[-3:])  # The last n-1 char\nprint(word[3:])   # All except the first 3 char\nprint(word[:-3])  # All except the last 3 char",
      "execution_count": 24,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "llo\nrld\nlo world\nHello wo\n"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Length of a text\nlen(word)",
      "execution_count": 5,
      "outputs": [
        {
          "data": {
            "text/plain": "11"
          },
          "execution_count": 5,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Place where a textual text is (first one to show)\nprint(\"Letter 'o' is @\",word.find(\"o\"))\nprint(\"Word 'world' starts @\", word.index(\"world\"))",
      "execution_count": 107,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "Letter %d is @ 4\nWord 'world' starts @ 6\n"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Frequency of a text\nprint(\"O's:\", word.count('o'))\nprint(\"Hello's:\", word.count('Hello'))",
      "execution_count": 14,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "O's: 2\nHello's: 1\n"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Split texts\nword.split(' ')",
      "execution_count": 50,
      "outputs": [
        {
          "data": {
            "text/plain": "['Hello', 'world']"
          },
          "execution_count": 50,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Replace string\nword.replace(\"Hello\", \"Goodbye\")",
      "execution_count": 32,
      "outputs": [
        {
          "data": {
            "text/plain": "'Goodbye world'"
          },
          "execution_count": 32,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Changing Upper and Lower Case Strings\nprint(word.upper())         # All upper case\nprint(word.lower())         # All lower case\nprint(word.title())         # All first letters in upper case\nprint(word.capitalize())    # Just first letter upper case",
      "execution_count": 36,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "HELLO WORLD\nhello world\nHello World\nHello world\n"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Repeat text n times\nprint(\":) | \"* 10)",
      "execution_count": 47,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": ":) | :) | :) | :) | :) | :) | :) | :) | :) | :) | \n"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Some boolean checks\nprint(word.isalnum())         # Check if all char are alphanumeric \nprint(word.isalpha())         # Check if all char in the string are alphabetic\nprint(word.isdigit())         # Test if string contains digits\nprint(word.istitle())         # Test if string contains title words\nprint(word.isupper())         # Test if string contains upper case\nprint(word.islower())         # Test if string contains lower case\nprint(word.isspace())         # Test if string consists on spaces\nprint(word.endswith('d'))     # Test if string endswith\nprint(word.startswith('H'))   # Test if string startswith ",
      "execution_count": 198,
      "outputs": [
        {
          "output_type": "stream",
          "text": "False\nFalse\nFalse\nFalse\nFalse\nFalse\nFalse\nTrue\nTrue\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Contains text in another text\ntexts = ['Primer texto','Segundo texto','Tercer']\nprint(\"'text' is in the first row:\",\"text\" in texts[0])        # Is a text in a text\nprint(\"'Cuarto' is somewhere:\",\"Cuarto\" in texts)              # Is there a row that is",
      "execution_count": 199,
      "outputs": [
        {
          "output_type": "stream",
          "text": "'text' is in the first row: True\n'Cuarto' is somewhere: False\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Filter rows which contains\nlist(filter(lambda x:'tex' in x, texts))",
      "execution_count": 206,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 206,
          "data": {
            "text/plain": "['Primer texto', 'Segundo texto']"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# Contains text in each row in a list\ncontains_text = []\nfor i in range(len(texts)):\n    contains_text.append(\"text\" in texts[i])\nprint(contains_text)",
      "execution_count": 200,
      "outputs": [
        {
          "output_type": "stream",
          "text": "[True, True, False]\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "_draft": {
      "nbviewer_url": "https://gist.github.com/4bf65e993789abfbeee2e52331c90c20"
    },
    "gist": {
      "id": "4bf65e993789abfbeee2e52331c90c20",
      "data": {
        "description": "strings and text",
        "public": true
      }
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.6.3",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}