{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "view-in-github"
},
"source": [
"<a href=\"https://colab.research.google.com/github/riyajaiswal25/MLProjects/blob/main/DigitRecognitionusingRandomForestClassifier.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "hdd4dapuroBk"
},
"source": [
"# Digit Recognition using Random Forest Classifier"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "k_cWcYTUsWdE"
},
"source": [
"**Import Basic Library**"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "t6uu8CVZrllI"
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "S_X9qpm0s4uq"
},
"source": [
"**Choosing Dataset**"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 73
},
"id": "ERRZ3tkOOYFA",
"outputId": "5f8f4aae-398b-4e33-e2c2-53de23174401"
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" <input type=\"file\" id=\"files-7634f8da-a56b-480e-a6d2-1cc2533a486a\" name=\"files[]\" multiple disabled\n",
" style=\"border:none\" />\n",
" <output id=\"result-7634f8da-a56b-480e-a6d2-1cc2533a486a\">\n",
" Upload widget is only available when the cell has been executed in the\n",
" current browser session. Please rerun this cell to enable.\n",
" </output>\n",
" <script>// Copyright 2017 Google LLC\n",
"//\n",
"// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
"// you may not use this file except in compliance with the License.\n",
"// You may obtain a copy of the License at\n",
"//\n",
"// http://www.apache.org/licenses/LICENSE-2.0\n",
"//\n",
"// Unless required by applicable law or agreed to in writing, software\n",
"// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
"// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
"// See the License for the specific language governing permissions and\n",
"// limitations under the License.\n",
"\n",
"/**\n",
" * @fileoverview Helpers for google.colab Python module.\n",
" */\n",
"(function(scope) {\n",
"function span(text, styleAttributes = {}) {\n",
" const element = document.createElement('span');\n",
" element.textContent = text;\n",
" for (const key of Object.keys(styleAttributes)) {\n",
" element.style[key] = styleAttributes[key];\n",
" }\n",
" return element;\n",
"}\n",
"\n",
"// Max number of bytes which will be uploaded at a time.\n",
"const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
"\n",
"function _uploadFiles(inputId, outputId) {\n",
" const steps = uploadFilesStep(inputId, outputId);\n",
" const outputElement = document.getElementById(outputId);\n",
" // Cache steps on the outputElement to make it available for the next call\n",
" // to uploadFilesContinue from Python.\n",
" outputElement.steps = steps;\n",
"\n",
" return _uploadFilesContinue(outputId);\n",
"}\n",
"\n",
"// This is roughly an async generator (not supported in the browser yet),\n",
"// where there are multiple asynchronous steps and the Python side is going\n",
"// to poll for completion of each step.\n",
"// This uses a Promise to block the python side on completion of each step,\n",
"// then passes the result of the previous step as the input to the next step.\n",
"function _uploadFilesContinue(outputId) {\n",
" const outputElement = document.getElementById(outputId);\n",
" const steps = outputElement.steps;\n",
"\n",
" const next = steps.next(outputElement.lastPromiseValue);\n",
" return Promise.resolve(next.value.promise).then((value) => {\n",
" // Cache the last promise value to make it available to the next\n",
" // step of the generator.\n",
" outputElement.lastPromiseValue = value;\n",
" return next.value.response;\n",
" });\n",
"}\n",
"\n",
"/**\n",
" * Generator function which is called between each async step of the upload\n",
" * process.\n",
" * @param {string} inputId Element ID of the input file picker element.\n",
" * @param {string} outputId Element ID of the output display.\n",
" * @return {!Iterable<!Object>} Iterable of next steps.\n",
" */\n",
"function* uploadFilesStep(inputId, outputId) {\n",
" const inputElement = document.getElementById(inputId);\n",
" inputElement.disabled = false;\n",
"\n",
" const outputElement = document.getElementById(outputId);\n",
" outputElement.innerHTML = '';\n",
"\n",
" const pickedPromise = new Promise((resolve) => {\n",
" inputElement.addEventListener('change', (e) => {\n",
" resolve(e.target.files);\n",
" });\n",
" });\n",
"\n",
" const cancel = document.createElement('button');\n",
" inputElement.parentElement.appendChild(cancel);\n",
" cancel.textContent = 'Cancel upload';\n",
" const cancelPromise = new Promise((resolve) => {\n",
" cancel.onclick = () => {\n",
" resolve(null);\n",
" };\n",
" });\n",
"\n",
" // Wait for the user to pick the files.\n",
" const files = yield {\n",
" promise: Promise.race([pickedPromise, cancelPromise]),\n",
" response: {\n",
" action: 'starting',\n",
" }\n",
" };\n",
"\n",
" cancel.remove();\n",
"\n",
" // Disable the input element since further picks are not allowed.\n",
" inputElement.disabled = true;\n",
"\n",
" if (!files) {\n",
" return {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
" }\n",
"\n",
" for (const file of files) {\n",
" const li = document.createElement('li');\n",
" li.append(span(file.name, {fontWeight: 'bold'}));\n",
" li.append(span(\n",
" `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
" `last modified: ${\n",
" file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
" 'n/a'} - `));\n",
" const percent = span('0% done');\n",
" li.appendChild(percent);\n",
"\n",
" outputElement.appendChild(li);\n",
"\n",
" const fileDataPromise = new Promise((resolve) => {\n",
" const reader = new FileReader();\n",
" reader.onload = (e) => {\n",
" resolve(e.target.result);\n",
" };\n",
" reader.readAsArrayBuffer(file);\n",
" });\n",
" // Wait for the data to be ready.\n",
" let fileData = yield {\n",
" promise: fileDataPromise,\n",
" response: {\n",
" action: 'continue',\n",
" }\n",
" };\n",
"\n",
" // Use a chunked sending to avoid message size limits. See b/62115660.\n",
" let position = 0;\n",
" do {\n",
" const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
" const chunk = new Uint8Array(fileData, position, length);\n",
" position += length;\n",
"\n",
" const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
" yield {\n",
" response: {\n",
" action: 'append',\n",
" file: file.name,\n",
" data: base64,\n",
" },\n",
" };\n",
"\n",
" let percentDone = fileData.byteLength === 0 ?\n",
" 100 :\n",
" Math.round((position / fileData.byteLength) * 100);\n",
" percent.textContent = `${percentDone}% done`;\n",
"\n",
" } while (position < fileData.byteLength);\n",
" }\n",
"\n",
" // All done.\n",
" yield {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
"}\n",
"\n",
"scope.google = scope.google || {};\n",
"scope.google.colab = scope.google.colab || {};\n",
"scope.google.colab._files = {\n",
" _uploadFiles,\n",
" _uploadFilesContinue,\n",
"};\n",
"})(self);\n",
"</script> "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Saving train[1].csv to train[1].csv\n"
]
}
],
"source": [
"from google.colab import files\n",
"uploaded = files.upload()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "TJRApm0w0Dct"
},
"source": [
"**Load Dataset**"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "GyOvJOoR0Lhq"
},
"outputs": [],
"source": [
"dataset = pd.read_csv('train.csv')"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0txmydWY0ZEH"
},
"source": [
"**Summarize dataset**"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "AW-9ITV10cIY",
"outputId": "dce2cb6d-2bdb-41e5-de9e-baf122900140"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(42000, 785)\n",
" label pixel0 pixel1 pixel2 pixel3 pixel4 pixel5 pixel6 pixel7 \\\n",
"0 1 0 0 0 0 0 0 0 0 \n",
"1 0 0 0 0 0 0 0 0 0 \n",
"2 1 0 0 0 0 0 0 0 0 \n",
"3 4 0 0 0 0 0 0 0 0 \n",
"4 0 0 0 0 0 0 0 0 0 \n",
"\n",
" pixel8 ... pixel774 pixel775 pixel776 pixel777 pixel778 pixel779 \\\n",
"0 0 ... 0 0 0 0 0 0 \n",
"1 0 ... 0 0 0 0 0 0 \n",
"2 0 ... 0 0 0 0 0 0 \n",
"3 0 ... 0 0 0 0 0 0 \n",
"4 0 ... 0 0 0 0 0 0 \n",
"\n",
" pixel780 pixel781 pixel782 pixel783 \n",
"0 0 0 0 0 \n",
"1 0 0 0 0 \n",
"2 0 0 0 0 \n",
"3 0 0 0 0 \n",
"4 0 0 0 0 \n",
"\n",
"[5 rows x 785 columns]\n"
]
}
],
"source": [
"print(dataset.shape)\n",
"print(dataset.head(5))"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "QUh5BKq20viv"
},
"source": [
"**Segregate Dataset into X(Input/Independent Variable) & Y(Output/Dependent Variable)**"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "OP2TX3iX09ND",
"outputId": "9c8f44e2-a503-4acf-8978-f6576706e402"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" pixel0 pixel1 pixel2 pixel3 pixel4 pixel5 pixel6 pixel7 pixel8 \\\n",
"0 0 0 0 0 0 0 0 0 0 \n",
"1 0 0 0 0 0 0 0 0 0 \n",
"2 0 0 0 0 0 0 0 0 0 \n",
"3 0 0 0 0 0 0 0 0 0 \n",
"4 0 0 0 0 0 0 0 0 0 \n",
"... ... ... ... ... ... ... ... ... ... \n",
"41995 0 0 0 0 0 0 0 0 0 \n",
"41996 0 0 0 0 0 0 0 0 0 \n",
"41997 0 0 0 0 0 0 0 0 0 \n",
"41998 0 0 0 0 0 0 0 0 0 \n",
"41999 0 0 0 0 0 0 0 0 0 \n",
"\n",
" pixel9 ... pixel774 pixel775 pixel776 pixel777 pixel778 \\\n",
"0 0 ... 0 0 0 0 0 \n",
"1 0 ... 0 0 0 0 0 \n",
"2 0 ... 0 0 0 0 0 \n",
"3 0 ... 0 0 0 0 0 \n",
"4 0 ... 0 0 0 0 0 \n",
"... ... ... ... ... ... ... ... \n",
"41995 0 ... 0 0 0 0 0 \n",
"41996 0 ... 0 0 0 0 0 \n",
"41997 0 ... 0 0 0 0 0 \n",
"41998 0 ... 0 0 0 0 0 \n",
"41999 0 ... 0 0 0 0 0 \n",
"\n",
" pixel779 pixel780 pixel781 pixel782 pixel783 \n",
"0 0 0 0 0 0 \n",
"1 0 0 0 0 0 \n",
"2 0 0 0 0 0 \n",
"3 0 0 0 0 0 \n",
"4 0 0 0 0 0 \n",
"... ... ... ... ... ... \n",
"41995 0 0 0 0 0 \n",
"41996 0 0 0 0 0 \n",
"41997 0 0 0 0 0 \n",
"41998 0 0 0 0 0 \n",
"41999 0 0 0 0 0 \n",
"\n",
"[42000 rows x 784 columns]\n",
"(42000, 784)\n"
]
}
],
"source": [
"X = dataset.iloc[:,1:]\n",
"print(X)\n",
"print(X.shape)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2RuBl7671GH4",
"outputId": "96d6afef-f2ed-420f-d95c-826a287fa8dd"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0 1\n",
"1 0\n",
"2 1\n",
"3 4\n",
"4 0\n",
" ..\n",
"41995 0\n",
"41996 1\n",
"41997 7\n",
"41998 6\n",
"41999 9\n",
"Name: label, Length: 42000, dtype: int64\n",
"(42000,)\n"
]
}
],
"source": [
"Y = dataset.iloc[:,0]\n",
"print(Y)\n",
"print(Y.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "o1j-AGZd1OQV"
},
"source": [
"**Splitting Dataset into Test and Train**"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"id": "U_c_R4HA1SeZ"
},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"X_train, X_test, y_train, y_test = train_test_split(X,Y, test_size = 0.25, random_state = 0)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Gf6EgvAc1vjh"
},
"source": [
"**Training**"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "RS4TAnDh1yUU",
"outputId": "4803259d-f3a1-461f-d3d0-939bc4495a64"
},
"outputs": [
{
"data": {
"text/plain": [
"RandomForestClassifier()"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from sklearn.ensemble import RandomForestClassifier\n",
"model = RandomForestClassifier()\n",
"model.fit(X_train, y_train)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"id": "SljeEEbs2JFT"
},
"outputs": [],
"source": [
"y_pred = model.predict(X_test)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "4XEvHILm2OF-"
},
"source": [
"**Model Accuracy**"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "sHEVc1Qq2Rqy",
"outputId": "06be6e32-1ba4-4035-eafb-3b3c2023abd6"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy of the Model: 96.31428571428572%\n"
]
}
],
"source": [
"from sklearn.metrics import accuracy_score\n",
"print(\"Accuracy of the Model: {0}%\".format(accuracy_score(y_test, y_pred)*100))"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 283
},
"id": "iymJ1Zpj20gk",
"outputId": "ae21ce24-b957-4a30-8f04-ec5c77dd5a53"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Predicted 7\n"
]
},
{
"data": {
"text/plain": [
"<matplotlib.image.AxesImage at 0x7ff128cbac90>"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"index=10\n",
"print(\"Predicted \" +str(model.predict(X_test)[index]))\n",
"plt.axis('off')\n",
"plt.imshow(X_test.iloc[index].values.reshape((28,28)),cmap='gray')"
]
}
],
"metadata": {
"colab": {
"authorship_tag": "ABX9TyOBzEe2vR1rQh4B8yWT0mhr",
"include_colab_link": true,
"provenance": []
},
"kernelspec": {
"display_name": "Python 3.8.9 64-bit",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.8.9"
},
"vscode": {
"interpreter": {
"hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
}
}
},
"nbformat": 4,
"nbformat_minor": 0
}