data_cleaning/02-scaling-and-normalization.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5f776215",
   "metadata": {
    "papermill": {
     "duration": 0.018549,
     "end_time": "2021-08-22T01:59:09.686006",
     "exception": false,
     "start_time": "2021-08-22T01:59:09.667457",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**This notebook is an exercise in the [Data Cleaning](https://www.kaggle.com/learn/data-cleaning) course.  You can reference the tutorial at [this link](https://www.kaggle.com/alexisbcook/scaling-and-normalization).**\n",
    "\n",
    "---\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a42c864b",
   "metadata": {
    "papermill": {
     "duration": 0.017725,
     "end_time": "2021-08-22T01:59:09.723958",
     "exception": false,
     "start_time": "2021-08-22T01:59:09.706233",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "In this exercise, you'll apply what you learned in the **Scaling and normalization** tutorial.\n",
    "\n",
    "# Setup\n",
    "\n",
    "The questions below will give you feedback on your work. Run the following cell to set up the feedback system."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e518113e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:09.771396Z",
     "iopub.status.busy": "2021-08-22T01:59:09.770575Z",
     "iopub.status.idle": "2021-08-22T01:59:13.508407Z",
     "shell.execute_reply": "2021-08-22T01:59:13.507524Z",
     "shell.execute_reply.started": "2021-08-22T01:44:40.317537Z"
    },
    "papermill": {
     "duration": 3.767252,
     "end_time": "2021-08-22T01:59:13.508653",
     "exception": false,
     "start_time": "2021-08-22T01:59:09.741401",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Setup Complete\n"
     ]
    }
   ],
   "source": [
    "from learntools.core import binder\n",
    "binder.bind(globals())\n",
    "from learntools.data_cleaning.ex2 import *\n",
    "print(\"Setup Complete\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a9d9839a",
   "metadata": {
    "papermill": {
     "duration": 0.018611,
     "end_time": "2021-08-22T01:59:13.546240",
     "exception": false,
     "start_time": "2021-08-22T01:59:13.527629",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Get our environment set up\n",
    "\n",
    "To practice scaling and normalization, we're going to use a [dataset of Kickstarter campaigns](https://www.kaggle.com/kemical/kickstarter-projects). (Kickstarter is a website where people can ask people to invest in various projects and concept products.)\n",
    "\n",
    "The next code cell loads in the libraries and dataset we'll be using. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6f7d5aff",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:13.588414Z",
     "iopub.status.busy": "2021-08-22T01:59:13.587608Z",
     "iopub.status.idle": "2021-08-22T01:59:15.176181Z",
     "shell.execute_reply": "2021-08-22T01:59:15.176727Z",
     "shell.execute_reply.started": "2021-08-22T01:45:00.661073Z"
    },
    "papermill": {
     "duration": 1.612054,
     "end_time": "2021-08-22T01:59:15.176968",
     "exception": false,
     "start_time": "2021-08-22T01:59:13.564914",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# modules we'll use\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "# for Box-Cox Transformation\n",
    "from scipy import stats\n",
    "\n",
    "# for min_max scaling\n",
    "from mlxtend.preprocessing import minmax_scaling\n",
    "\n",
    "# plotting modules\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# read in all our data\n",
    "kickstarters_2017 = pd.read_csv(\"../input/kickstarter-projects/ks-projects-201801.csv\")\n",
    "\n",
    "# set seed for reproducibility\n",
    "np.random.seed(0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3d87e129",
   "metadata": {
    "papermill": {
     "duration": 0.019995,
     "end_time": "2021-08-22T01:59:15.215865",
     "exception": false,
     "start_time": "2021-08-22T01:59:15.195870",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Let's start by scaling the goals of each campaign, which is how much money they were asking for.  The plots show a histogram of the values in the \"usd_goal_real\" column, both before and after scaling.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6f73afae",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:15.263259Z",
     "iopub.status.busy": "2021-08-22T01:59:15.262463Z",
     "iopub.status.idle": "2021-08-22T01:59:19.007683Z",
     "shell.execute_reply": "2021-08-22T01:59:19.007081Z",
     "shell.execute_reply.started": "2021-08-22T01:45:49.902455Z"
    },
    "papermill": {
     "duration": 3.773325,
     "end_time": "2021-08-22T01:59:19.007859",
     "exception": false,
     "start_time": "2021-08-22T01:59:15.234534",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.7/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "  warnings.warn(msg, FutureWarning)\n",
      "/opt/conda/lib/python3.7/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "  warnings.warn(msg, FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Scaled data')"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x216 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# select the usd_goal_real column\n",
    "original_data = pd.DataFrame(kickstarters_2017.usd_goal_real)\n",
    "\n",
    "# scale the goals from 0 to 1\n",
    "scaled_data = minmax_scaling(original_data, columns=['usd_goal_real'])\n",
    "\n",
    "# plot the original & scaled data together to compare\n",
    "fig, ax=plt.subplots(1,2,figsize=(15,3))\n",
    "sns.distplot(kickstarters_2017.usd_goal_real, ax=ax[0])\n",
    "ax[0].set_title(\"Original Data\")\n",
    "sns.distplot(scaled_data, ax=ax[1])\n",
    "ax[1].set_title(\"Scaled data\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1037cb06",
   "metadata": {
    "papermill": {
     "duration": 0.019026,
     "end_time": "2021-08-22T01:59:19.047140",
     "exception": false,
     "start_time": "2021-08-22T01:59:19.028114",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "After scaling, all values lie between 0 and 1 (you can read this in the horizontal axis of the second plot above, and we verify in the code cell below)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1cdd610f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:19.097733Z",
     "iopub.status.busy": "2021-08-22T01:59:19.095957Z",
     "iopub.status.idle": "2021-08-22T01:59:19.115637Z",
     "shell.execute_reply": "2021-08-22T01:59:19.114867Z",
     "shell.execute_reply.started": "2021-08-22T01:46:34.910836Z"
    },
    "papermill": {
     "duration": 0.04858,
     "end_time": "2021-08-22T01:59:19.115817",
     "exception": false,
     "start_time": "2021-08-22T01:59:19.067237",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Original data\n",
      "Preview:\n",
      "    usd_goal_real\n",
      "0        1533.95\n",
      "1       30000.00\n",
      "2       45000.00\n",
      "3        5000.00\n",
      "4       19500.00\n",
      "Minimum value: 0.01 \n",
      "Maximum value: 166361390.71\n",
      "______________________________\n",
      "\n",
      "Scaled data\n",
      "Preview:\n",
      "    usd_goal_real\n",
      "0       0.000009\n",
      "1       0.000180\n",
      "2       0.000270\n",
      "3       0.000030\n",
      "4       0.000117\n",
      "Minimum value: 0.0 \n",
      "Maximum value: 1.0\n"
     ]
    }
   ],
   "source": [
    "print('Original data\\nPreview:\\n', original_data.head())\n",
    "print('Minimum value:', float(original_data.min()),\n",
    "      '\\nMaximum value:', float(original_data.max()))\n",
    "print('_'*30)\n",
    "\n",
    "print('\\nScaled data\\nPreview:\\n', scaled_data.head())\n",
    "print('Minimum value:', float(scaled_data.min()),\n",
    "      '\\nMaximum value:', float(scaled_data.max()))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ed1e9a6d",
   "metadata": {
    "papermill": {
     "duration": 0.019385,
     "end_time": "2021-08-22T01:59:19.155009",
     "exception": false,
     "start_time": "2021-08-22T01:59:19.135624",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# 1) Practice scaling\n",
    "\n",
    "We just scaled the \"usd_goal_real\" column. What about the \"goal\" column?\n",
    "\n",
    "Begin by running the code cell below to create a DataFrame `original_goal_data` containing the \"goal\" column."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "f9bd78b3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:19.200583Z",
     "iopub.status.busy": "2021-08-22T01:59:19.199714Z",
     "iopub.status.idle": "2021-08-22T01:59:19.204056Z",
     "shell.execute_reply": "2021-08-22T01:59:19.203469Z",
     "shell.execute_reply.started": "2021-08-22T01:47:30.915833Z"
    },
    "papermill": {
     "duration": 0.029309,
     "end_time": "2021-08-22T01:59:19.204213",
     "exception": false,
     "start_time": "2021-08-22T01:59:19.174904",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# select the usd_goal_real column\n",
    "original_goal_data = pd.DataFrame(kickstarters_2017.goal)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "05ea0f46",
   "metadata": {
    "papermill": {
     "duration": 0.022608,
     "end_time": "2021-08-22T01:59:19.246717",
     "exception": false,
     "start_time": "2021-08-22T01:59:19.224109",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Use `original_goal_data` to create a new DataFrame `scaled_goal_data` with values scaled between 0 and 1. You must use the `minmax_scaling()` function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "40493be4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:19.291947Z",
     "iopub.status.busy": "2021-08-22T01:59:19.291121Z",
     "iopub.status.idle": "2021-08-22T01:59:19.318884Z",
     "shell.execute_reply": "2021-08-22T01:59:19.318181Z",
     "shell.execute_reply.started": "2021-08-22T01:48:15.705361Z"
    },
    "papermill": {
     "duration": 0.052465,
     "end_time": "2021-08-22T01:59:19.319054",
     "exception": false,
     "start_time": "2021-08-22T01:59:19.266589",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "parent.postMessage({\"jupyterEvent\": \"custom.exercise_interaction\", \"data\": {\"outcomeType\": 1, \"valueTowardsCompletion\": 0.3333333333333333, \"interactionType\": 1, \"questionType\": 1, \"questionId\": \"1_TryScaling\", \"learnToolsVersion\": \"0.3.4\", \"failureMessage\": \"\", \"exceptionClass\": \"\", \"trace\": \"\"}}, \"*\")"
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/markdown": [
       "<span style=\"color:#33cc33\">Correct</span>"
      ],
      "text/plain": [
       "Correct"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# TODO: Your code here\n",
    "scaled_goal_data = minmax_scaling(original_goal_data, columns=['goal'])\n",
    "\n",
    "# Check your answer\n",
    "q1.check()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "8bece058",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:19.369889Z",
     "iopub.status.busy": "2021-08-22T01:59:19.368777Z",
     "iopub.status.idle": "2021-08-22T01:59:19.372268Z",
     "shell.execute_reply": "2021-08-22T01:59:19.372789Z",
     "shell.execute_reply.started": "2021-08-22T01:48:19.661730Z"
    },
    "papermill": {
     "duration": 0.03094,
     "end_time": "2021-08-22T01:59:19.373008",
     "exception": false,
     "start_time": "2021-08-22T01:59:19.342068",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Lines below will give you a hint or solution code\n",
    "#q1.hint()\n",
    "#q1.solution()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8badaf2f",
   "metadata": {
    "papermill": {
     "duration": 0.021758,
     "end_time": "2021-08-22T01:59:19.416520",
     "exception": false,
     "start_time": "2021-08-22T01:59:19.394762",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# 2) Practice normalization\n",
    "\n",
    "Now you'll practice normalization. We begin by normalizing the amount of money pledged to each campaign."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d5e763d9",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:19.468096Z",
     "iopub.status.busy": "2021-08-22T01:59:19.466934Z",
     "iopub.status.idle": "2021-08-22T01:59:23.759351Z",
     "shell.execute_reply": "2021-08-22T01:59:23.759986Z",
     "shell.execute_reply.started": "2021-08-22T01:49:56.703136Z"
    },
    "papermill": {
     "duration": 4.322936,
     "end_time": "2021-08-22T01:59:23.760209",
     "exception": false,
     "start_time": "2021-08-22T01:59:19.437273",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.7/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "  warnings.warn(msg, FutureWarning)\n",
      "/opt/conda/lib/python3.7/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "  warnings.warn(msg, FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Normalized data')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x216 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# get the index of all positive pledges (Box-Cox only takes positive values)\n",
    "index_of_positive_pledges = kickstarters_2017.usd_pledged_real > 0\n",
    "\n",
    "# get only positive pledges (using their indexes)\n",
    "positive_pledges = kickstarters_2017.usd_pledged_real.loc[index_of_positive_pledges]\n",
    "\n",
    "# normalize the pledges (w/ Box-Cox)\n",
    "normalized_pledges = pd.Series(stats.boxcox(positive_pledges)[0], \n",
    "                               name='usd_pledged_real', index=positive_pledges.index)\n",
    "\n",
    "# plot both together to compare\n",
    "fig, ax=plt.subplots(1,2,figsize=(15,3))\n",
    "sns.distplot(positive_pledges, ax=ax[0])\n",
    "ax[0].set_title(\"Original Data\")\n",
    "sns.distplot(normalized_pledges, ax=ax[1])\n",
    "ax[1].set_title(\"Normalized data\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d219bbef",
   "metadata": {
    "papermill": {
     "duration": 0.026627,
     "end_time": "2021-08-22T01:59:23.812420",
     "exception": false,
     "start_time": "2021-08-22T01:59:23.785793",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "It's not perfect (it looks like a lot pledges got very few pledges) but it is much closer to a normal distribution!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "b27386a6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:23.866660Z",
     "iopub.status.busy": "2021-08-22T01:59:23.865881Z",
     "iopub.status.idle": "2021-08-22T01:59:23.874957Z",
     "shell.execute_reply": "2021-08-22T01:59:23.875749Z",
     "shell.execute_reply.started": "2021-08-22T01:50:29.577512Z"
    },
    "papermill": {
     "duration": 0.040656,
     "end_time": "2021-08-22T01:59:23.876124",
     "exception": false,
     "start_time": "2021-08-22T01:59:23.835468",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Original data\n",
      "Preview:\n",
      " 1     2421.0\n",
      "2      220.0\n",
      "3        1.0\n",
      "4     1283.0\n",
      "5    52375.0\n",
      "Name: usd_pledged_real, dtype: float64\n",
      "Minimum value: 0.45 \n",
      "Maximum value: 20338986.27\n",
      "______________________________\n",
      "\n",
      "Normalized data\n",
      "Preview:\n",
      " 1    10.165142\n",
      "2     6.468598\n",
      "3     0.000000\n",
      "4     9.129277\n",
      "5    15.836853\n",
      "Name: usd_pledged_real, dtype: float64\n",
      "Minimum value: -0.7779954122762203 \n",
      "Maximum value: 30.69054020451361\n"
     ]
    }
   ],
   "source": [
    "print('Original data\\nPreview:\\n', positive_pledges.head())\n",
    "print('Minimum value:', float(positive_pledges.min()),\n",
    "      '\\nMaximum value:', float(positive_pledges.max()))\n",
    "print('_'*30)\n",
    "\n",
    "print('\\nNormalized data\\nPreview:\\n', normalized_pledges.head())\n",
    "print('Minimum value:', float(normalized_pledges.min()),\n",
    "      '\\nMaximum value:', float(normalized_pledges.max()))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dc321811",
   "metadata": {
    "papermill": {
     "duration": 0.02523,
     "end_time": "2021-08-22T01:59:23.929140",
     "exception": false,
     "start_time": "2021-08-22T01:59:23.903910",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "We used the \"usd_pledged_real\" column. Follow the same process to normalize the \"pledged\" column. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "0997f760",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:23.988204Z",
     "iopub.status.busy": "2021-08-22T01:59:23.987443Z",
     "iopub.status.idle": "2021-08-22T01:59:28.258751Z",
     "shell.execute_reply": "2021-08-22T01:59:28.258082Z",
     "shell.execute_reply.started": "2021-08-22T01:53:27.638086Z"
    },
    "papermill": {
     "duration": 4.3027,
     "end_time": "2021-08-22T01:59:28.258900",
     "exception": false,
     "start_time": "2021-08-22T01:59:23.956200",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.7/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "  warnings.warn(msg, FutureWarning)\n",
      "/opt/conda/lib/python3.7/site-packages/seaborn/distributions.py:2557: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).\n",
      "  warnings.warn(msg, FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Normalized data')"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x216 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# TODO: Your code here!\n",
    "# get only positive pledges (Box-Cox only takes positive values)\n",
    "positive_pledges = kickstarters_2017.pledged.loc[kickstarters_2017.pledged > 0]\n",
    "\n",
    "# normalize the pledges (w/ Box-Cox)\n",
    "normalized_pledges = pd.Series(stats.boxcox(positive_pledges)[0], \n",
    "                               name='pledged', index=positive_pledges.index)\n",
    "\n",
    "# plot both together to compare\n",
    "fig, ax=plt.subplots(1,2,figsize=(15,3))\n",
    "sns.distplot(positive_pledges, ax=ax[0])\n",
    "ax[0].set_title(\"Original Data\")\n",
    "sns.distplot(normalized_pledges, ax=ax[1])\n",
    "ax[1].set_title(\"Normalized data\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bb5013be",
   "metadata": {
    "papermill": {
     "duration": 0.02402,
     "end_time": "2021-08-22T01:59:28.307637",
     "exception": false,
     "start_time": "2021-08-22T01:59:28.283617",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "How does the normalized \"usd_pledged_real\" column look different from when we normalized the \"pledged\" column?  Or, do they look mostly the same?\n",
    "\n",
    "Once you have an answer, run the code cell below."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "c375fac0",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:28.362367Z",
     "iopub.status.busy": "2021-08-22T01:59:28.361367Z",
     "iopub.status.idle": "2021-08-22T01:59:28.369635Z",
     "shell.execute_reply": "2021-08-22T01:59:28.368984Z",
     "shell.execute_reply.started": "2021-08-22T01:54:05.653272Z"
    },
    "papermill": {
     "duration": 0.037725,
     "end_time": "2021-08-22T01:59:28.369778",
     "exception": false,
     "start_time": "2021-08-22T01:59:28.332053",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "application/javascript": [
       "parent.postMessage({\"jupyterEvent\": \"custom.exercise_interaction\", \"data\": {\"outcomeType\": 1, \"valueTowardsCompletion\": 0.3333333333333333, \"interactionType\": 1, \"questionType\": 4, \"questionId\": \"2_TryNormalization\", \"learnToolsVersion\": \"0.3.4\", \"failureMessage\": \"\", \"exceptionClass\": \"\", \"trace\": \"\"}}, \"*\")"
      ],
      "text/plain": [
       "<IPython.core.display.Javascript object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/markdown": [
       "<span style=\"color:#33cc33\">Correct:</span> \n",
       "\n",
       "The distributions in the normalized data look mostly the same."
      ],
      "text/plain": [
       "Correct: \n",
       "\n",
       "The distributions in the normalized data look mostly the same."
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Check your answer (Run this code cell to receive credit!)\n",
    "q2.check()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "3ead7f1f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-08-22T01:59:28.425957Z",
     "iopub.status.busy": "2021-08-22T01:59:28.425093Z",
     "iopub.status.idle": "2021-08-22T01:59:28.428971Z",
     "shell.execute_reply": "2021-08-22T01:59:28.428369Z",
     "shell.execute_reply.started": "2021-08-22T01:57:07.782195Z"
    },
    "papermill": {
     "duration": 0.033461,
     "end_time": "2021-08-22T01:59:28.429112",
     "exception": false,
     "start_time": "2021-08-22T01:59:28.395651",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Line below will give you a hint\n",
    "#q2.hint()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2170c14f",
   "metadata": {
    "papermill": {
     "duration": 0.025736,
     "end_time": "2021-08-22T01:59:28.480679",
     "exception": false,
     "start_time": "2021-08-22T01:59:28.454943",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# (Optional) More practice\n",
    "\n",
    "Try finding a new dataset and pretend you're preparing to perform a [regression analysis](https://www.kaggle.com/rtatman/the-5-day-regression-challenge). \n",
    "\n",
    "[These datasets are a good start!](https://www.kaggle.com/rtatman/datasets-for-regression-analysis)\n",
    "\n",
    "Pick three or four variables and decide if you need to normalize or scale any of them and, if you think you should, practice applying the correct technique.\n",
    "\n",
    "# Keep going\n",
    "\n",
    "In the next lesson, learn how to [**parse dates**](https://www.kaggle.com/alexisbcook/parsing-dates) in a dataset."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0698ecb2",
   "metadata": {
    "papermill": {
     "duration": 0.025474,
     "end_time": "2021-08-22T01:59:28.531824",
     "exception": false,
     "start_time": "2021-08-22T01:59:28.506350",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "---\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "*Have questions or comments? Visit the [Learn Discussion forum](https://www.kaggle.com/learn-forum/172650) to chat with other Learners.*"
   ]
  }
 ],
 "metadata": {
  "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": "3.7.10"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 28.532234,
   "end_time": "2021-08-22T01:59:29.469941",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2021-08-22T01:59:00.937707",
   "version": "2.3.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}