Add files via upload

Progress bar in Jupyter notebook for tracking the progress as your machine learning model is training

python/model_is_training_progress_bar.ipynb

@@ -0,0 +1,208 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "zzD4-HxqXBmt"
+   },
+   "source": [
+    "# **Progress Bar in Jupyter Notebook**\n",
+    "\n",
+    "Chanin Nantasenamat\n",
+    "\n",
+    "**Data Professor YouTube channel**, http://youtube.com/dataprofessor"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "An7XU557Y5ci"
+   },
+   "source": [
+    "# **Progress Bar with the tqdm library**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "3yc04janmetd"
+   },
+   "outputs": [],
+   "source": [
+    "# ! pip install tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "gxa8jup1DNjt"
+   },
+   "outputs": [],
+   "source": [
+    "from tqdm.notebook import tqdm\n",
+    "from time import sleep"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "009bdoXCE74q"
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "93cc2d7933af4faf96fda14e55f24e23",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/100 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "number_list = list(range(100))\n",
+    "for x in tqdm(number_list):\n",
+    "    sleep(0.05)\n",
+    "#print('Completed!')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "4tFGw2QFMz6N"
+   },
+   "source": [
+    "# **Model Building**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "zKKr9EoSVbOV"
+   },
+   "source": [
+    "### Reading in the Delaney Solubility Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "FHR0FBHEMyyL"
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "dataset = pd.read_csv('https://raw.githubusercontent.com/dataprofessor/data/master/delaney_solubility_with_descriptors.csv')\n",
+    "\n",
+    "X = dataset.drop(['logS'], axis=1)\n",
+    "Y = dataset.iloc[:,-1]\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "BqqRRTtUVi7v"
+   },
+   "source": [
+    "### Model Building with Progress Bar"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "cpa2tS3kInAx",
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a1b762495ff545468e8b801795c6b708",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/10 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tree: 100, R2: 0.9796508266364179, MSE: 0.08936295274735467\n",
+      "Tree: 200, R2: 0.9805478792326812, MSE: 0.08542356575902461\n",
+      "Tree: 300, R2: 0.9801470956638436, MSE: 0.08718359809468906\n",
+      "Tree: 400, R2: 0.9803760482277171, MSE: 0.08617815788435489\n",
+      "Tree: 500, R2: 0.9804686074892891, MSE: 0.08577168589797951\n",
+      "Tree: 600, R2: 0.9804079256830844, MSE: 0.08603816873163578\n",
+      "Tree: 700, R2: 0.9802975717717071, MSE: 0.0865227855360484\n",
+      "Tree: 800, R2: 0.9803651322114956, MSE: 0.08622609533244484\n",
+      "Tree: 900, R2: 0.98037907466393, MSE: 0.08616486735547396\n",
+      "Tree: 1000, R2: 0.9804349669126423, MSE: 0.08591941775949379\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import RandomForestRegressor\n",
+    "from sklearn.metrics import mean_squared_error, r2_score\n",
+    "\n",
+    "parameter_n_estimators = [100,200,300,400,500,600,700,800,900,1000]\n",
+    "\n",
+    "for i in tqdm(parameter_n_estimators):\n",
+    "  model = RandomForestRegressor(n_estimators=i)\n",
+    "  model.fit(X,Y)\n",
+    "  Y_pred = model.predict(X)\n",
+    "  r2 = r2_score(Y, Y_pred)\n",
+    "  mse = mean_squared_error(Y, Y_pred)\n",
+    "  print('Tree: %s, R2: %s, MSE: %s' % (i, r2, mse))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "collapsed_sections": [],
+   "name": "Model-building-with-progress-bar.ipynb",
+   "provenance": []
+  },
+  "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": "3.7.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}