Random_distribution(uniform,Normal,Binomial,Exponential).ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyMjax95hE4k6TTCIB/qEWHA",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/pawan-cpu/Types-of-machine-learning-Notebooks/blob/main/Random_distribution(uniform%2CNormal%2CBinomial%2CExponential).ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Working with probability distributions  helps us to find out the percentage distribution and certainity.\n",
        "#Uniform distribution(10,20) values are 11 12 13 14 15 16 17 18 19 20\n",
        "#we use uniform distribution to find the values in given range and values outside the range the data does not occur.We could use a density plot for\n",
        "#the uniform distribution appears flat."
      ],
      "metadata": {
        "id": "jnCFGIamKV6H"
      },
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "%matplotlib inline\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import scipy.stats as stats"
      ],
      "metadata": {
        "id": "xpdoBEiTKXWB"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "id": "gXWG_RET-DIg"
      },
      "outputs": [],
      "source": [
        "#Import module to create graph plots\n",
        "#what is variance\n",
        "#sample Variance (s^2)= summation(xi-Mean)^2/n-1\n",
        "\n",
        "#0 , 1 ,2,3,4,5...10,00,000"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "uniform_data= stats.uniform.rvs( size= 10000,  #generate 10000 numbers\n",
        "                                 loc=0,       #From 0\n",
        "                                 scale=10)    #To 10"
      ],
      "metadata": {
        "id": "lOIgYdp8NcUM"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pd.DataFrame(uniform_data).plot(kind = \"density\",  #plot the values\n",
        "                                figsize= (10,9),\n",
        "                                xlim=(-1,11));"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 753
        },
        "id": "06PpIzvkOHKL",
        "outputId": "cfd60b7c-dfd9-4564-e092-80688674cd27"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x900 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#create a quantile (percentile) comes under cumulative distribution function\n",
        "# It's not similar or equal to percentage\n",
        "#25 percentile mean 25 percent scored marks less than mass u got\n",
        "#cdf is cumulative data function(mean)\n",
        "\n",
        "stats.uniform.cdf(x=2,        #cutoff value (quantile)\n",
        "                  loc=0,      #distribution start\n",
        "                  scale=10)  #DISTRIBUTION END\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7fI7Gzu4BVbQ",
        "outputId": "4c6c2042-ccd7-4c27-f937-03a53fd82d4a"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.2"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#USING stats.distribution.ppf is inverse of cdf :It returns x axis cutopp value (quntile) associated with a given probability.\n",
        "stats.uniform.ppf(q = 0.4,      #probability cutoff\n",
        "                  loc = 0,      #distribution cutoff\n",
        "                  scale=10)  #Distribution end"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nO0plohgRLdd",
        "outputId": "1aa9de67-2279-47ce-e413-37d3eaaed811"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "4.0"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "and"
      ],
      "metadata": {
        "id": "VEmptsjoTpJ3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#using stats.pdf it eseasier to create a probability distribution for the x values in the range\n",
        "for x in range(-1,12,3):\n",
        "  print(\"Density at x value\"+ str(x))\n",
        "  print(stats.uniform.pdf(x,loc=0,scale=10))"
      ],
      "metadata": {
        "id": "UGd0cvCpZZOT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "4651794f-71cf-486d-dd75-a13f443904dd"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Density at x value-1\n",
            "0.0\n",
            "Density at x value2\n",
            "0.1\n",
            "Density at x value5\n",
            "0.1\n",
            "Density at x value8\n",
            "0.1\n",
            "Density at x value11\n",
            "0.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#generating random numbers and specify the seed\n",
        "#when u need to generate random real no in a range with equal probability you choose for  numbers from a uniform distribution\n",
        "import random\n",
        "random.randint(0,10) #get a random integer in the given range\n"
      ],
      "metadata": {
        "id": "uKyE10uLaiYZ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "39d78b82-9859-487d-a762-3277fae598f0"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "random.choice([2,4,6,9]) #get a random element from a sequence"
      ],
      "metadata": {
        "id": "TzF3r2gnbO2b",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "76d32740-1aec-4e80-a7e2-2576e2bbae77"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "2"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "random.random() #get any real number between 0 and 1"
      ],
      "metadata": {
        "id": "Hxq03zEAgSDL",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "3c7dc029-93a8-4bb6-ce50-72eda29c4b18"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.1253096111705162"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "random.uniform(0,10) #get a real no in the specified range\n",
        "\n",
        "#Integer:1,2,3\n",
        "#Real :3,3.0,3.3\n",
        "#whole no:0 ,1,2,3\n",
        "#positive integers(fist ten): 1,2,3,4,5,6,7,8,9,10"
      ],
      "metadata": {
        "id": "qV06EDeFVrbR",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "6ab3bb4c-0bc5-481b-96f5-c321297841a7"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "2.172783157576117"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "random.seed(12) #set any seed to arbitrary value\n",
        "print([random.uniform(0,10) for x in range(4)])\n",
        "random.seed(12) #set the seed to same value\n",
        "print([random.uniform(0,10) for x in range(4)])\n",
        "\n"
      ],
      "metadata": {
        "id": "mOAs1fiYim61",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d12db401-3b77-4a42-aa7f-a794e465887a"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[4.7457067868854805, 6.574725026572553, 6.664104711248381, 1.4260035292536777]\n",
            "[4.7457067868854805, 6.574725026572553, 6.664104711248381, 1.4260035292536777]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "L24v-D-UhRfV"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "UokL1J2LhSG2"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}