{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"toc_visible": true,
"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/graphmen/webgis/blob/main/PackagesPandas.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"source": [
"# Package\n",
"\n",
"In this section, we will learn about a few important packages including\n",
"\n",
"1. **Pandas**\n",
"2. Numpy\n",
"3. Scipy\n",
"4. Xarray"
],
"metadata": {
"id": "9cds9uDIxCra"
}
},
{
"cell_type": "markdown",
"source": [
"## Pandas\n",
"\n",
"We will learn how to use pandas to:\n",
"1. open files\n",
"2. perform basic statistics\n",
"3. special functions such as dropna, isin, groupby, apply\n",
"4. Resampling and filling missing values\n",
"5. Simple plotting\n",
"6. Exporting data\n"
],
"metadata": {
"id": "Xf0WLTd4xSRg"
}
},
{
"cell_type": "markdown",
"source": [
"Let's get our data from a Github public repository "
],
"metadata": {
"id": "KfEeHmFOyHkn"
}
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "8ASydfafwOG_",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "c3673c09-091a-44a7-d315-3cc377404213"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'CARNASRDA_python_training'...\n",
"remote: Enumerating objects: 44, done.\u001b[K\n",
"remote: Counting objects: 100% (44/44), done.\u001b[K\n",
"remote: Compressing objects: 100% (43/43), done.\u001b[K\n",
"remote: Total 44 (delta 16), reused 0 (delta 0), pack-reused 0\u001b[K\n",
"Unpacking objects: 100% (44/44), 6.64 MiB | 2.48 MiB/s, done.\n",
"/content/CARNASRDA_python_training\n",
"Data_acquisition.ipynb\t\t\tmodelling_prediction.ipynb\n",
"Data_processing_and_manipulation.ipynb\tosogbo.csv\n",
"Graphs_and_plots.ipynb\t\t\tplot_graphs.ipynb\n",
"import_data.ipynb\t\t\tProcessing_data.ipynb\n",
"LICENSE\t\t\t\t\tREADME.md\n",
"machine_learning.ipynb\n"
]
}
],
"source": [
"!git clone https://github.com/ogunjosam/CARNASRDA_python_training.git\n",
"\n",
"%cd CARNASRDA_python_training\n",
"\n",
"!dir"
]
},
{
"cell_type": "markdown",
"source": [
"We can use pandas to open files such as .csv, .xlsx, .sql etc"
],
"metadata": {
"id": "RBZu44VxzLpO"
}
},
{
"cell_type": "code",
"source": [
"import pandas as pd\n",
"\n",
"xx = pd.read_csv('osogbo.csv') # csv files\n",
"#xx = pd.read_excel('osogbo.xlsx')\n",
"\n",
"list(xx) # get the list of column names\n"
],
"metadata": {
"id": "YD-nh4O5zuTP",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "1c9ec8f0-693f-42ef-ee90-1b7eec3285cb"
},
"execution_count": 4,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['created_at',\n",
" 'entry_id',\n",
" 'PM1.0_CF1_ug/m3',\n",
" 'PM2.5_CF1_ug/m3',\n",
" 'PM10.0_CF1_ug/m3',\n",
" 'UptimeMinutes',\n",
" 'RSSI_dbm',\n",
" 'Temperature_F',\n",
" 'Humidity_%',\n",
" 'PM2.5_ATM_ug/m3',\n",
" 'Unnamed: 10']"
]
},
"metadata": {},
"execution_count": 4
}
]
},
{
"cell_type": "markdown",
"source": [
"We can set some parameters when importing"
],
"metadata": {
"id": "ohsEJ29K0JhO"
}
},
{
"cell_type": "markdown",
"source": [
"We can:\n",
"\n",
"* import only specific columns\n",
"* set our index parameter\n",
"\n"
],
"metadata": {
"id": "wUpQaQVd2Dn8"
}
},
{
"cell_type": "code",
"source": [
"xx = pd.read_csv('osogbo.csv',index_col='created_at',usecols=['created_at','PM1.0_CF1_ug/m3','PM2.5_CF1_ug/m3',\n",
" 'PM10.0_CF1_ug/m3','Temperature_F','Humidity_%'])\n",
"\n",
"\n"
],
"metadata": {
"id": "VZAuR47D2WL0",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 455
},
"outputId": "4ece9a4f-d2e3-43c9-9754-33633c00277c"
},
"execution_count": 6,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" PM1.0_CF1_ug/m3 PM2.5_CF1_ug/m3 PM10.0_CF1_ug/m3 \\\n",
"created_at \n",
"2021-01-01 00:01:14 UTC 48.24 72.73 83.95 \n",
"2021-01-01 00:03:14 UTC 48.18 72.32 81.34 \n",
"2021-01-01 00:05:14 UTC 48.95 74.23 83.46 \n",
"2021-01-01 00:07:14 UTC 47.47 73.09 82.78 \n",
"2021-01-01 00:09:14 UTC 48.09 72.57 82.44 \n",
"... ... ... ... \n",
"2021-12-31 23:50:51 UTC 52.54 70.86 88.53 \n",
"2021-12-31 23:52:51 UTC 53.40 72.86 90.23 \n",
"2021-12-31 23:54:51 UTC 51.96 70.60 87.96 \n",
"2021-12-31 23:56:49 UTC 53.50 71.91 85.33 \n",
"2021-12-31 23:58:50 UTC 52.23 71.63 90.40 \n",
"\n",
" Temperature_F Humidity_% \n",
"created_at \n",
"2021-01-01 00:01:14 UTC 78.0 59.0 \n",
"2021-01-01 00:03:14 UTC 78.0 59.0 \n",
"2021-01-01 00:05:14 UTC 78.0 59.0 \n",
"2021-01-01 00:07:14 UTC 78.0 59.0 \n",
"2021-01-01 00:09:14 UTC 78.0 58.0 \n",
"... ... ... \n",
"2021-12-31 23:50:51 UTC 82.0 55.0 \n",
"2021-12-31 23:52:51 UTC 82.0 55.0 \n",
"2021-12-31 23:54:51 UTC 82.0 55.0 \n",
"2021-12-31 23:56:49 UTC 82.0 55.0 \n",
"2021-12-31 23:58:50 UTC 82.0 55.0 \n",
"\n",
"[236400 rows x 5 columns]"
],
"text/html": [
"\n",
" <div id=\"df-244a074d-d148-4d6a-a2b8-8821020a7069\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PM1.0_CF1_ug/m3</th>\n",
" <th>PM2.5_CF1_ug/m3</th>\n",
" <th>PM10.0_CF1_ug/m3</th>\n",
" <th>Temperature_F</th>\n",
" <th>Humidity_%</th>\n",
" </tr>\n",
" <tr>\n",
" <th>created_at</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2021-01-01 00:01:14 UTC</th>\n",
" <td>48.24</td>\n",
" <td>72.73</td>\n",
" <td>83.95</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:03:14 UTC</th>\n",
" <td>48.18</td>\n",
" <td>72.32</td>\n",
" <td>81.34</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:05:14 UTC</th>\n",
" <td>48.95</td>\n",
" <td>74.23</td>\n",
" <td>83.46</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:07:14 UTC</th>\n",
" <td>47.47</td>\n",
" <td>73.09</td>\n",
" <td>82.78</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:09:14 UTC</th>\n",
" <td>48.09</td>\n",
" <td>72.57</td>\n",
" <td>82.44</td>\n",
" <td>78.0</td>\n",
" <td>58.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:50:51 UTC</th>\n",
" <td>52.54</td>\n",
" <td>70.86</td>\n",
" <td>88.53</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:52:51 UTC</th>\n",
" <td>53.40</td>\n",
" <td>72.86</td>\n",
" <td>90.23</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:54:51 UTC</th>\n",
" <td>51.96</td>\n",
" <td>70.60</td>\n",
" <td>87.96</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:56:49 UTC</th>\n",
" <td>53.50</td>\n",
" <td>71.91</td>\n",
" <td>85.33</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:58:50 UTC</th>\n",
" <td>52.23</td>\n",
" <td>71.63</td>\n",
" <td>90.40</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>236400 rows × 5 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-244a074d-d148-4d6a-a2b8-8821020a7069')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-244a074d-d148-4d6a-a2b8-8821020a7069 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-244a074d-d148-4d6a-a2b8-8821020a7069');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 6
}
]
},
{
"cell_type": "code",
"source": [
"# To get the best out of pandas dataframes with time, the index must be in datetime format. \n",
"#This is done with the line below\n",
"\n",
"xx.index = pd.DatetimeIndex(xx.index)\n",
"xx"
],
"metadata": {
"id": "wPMGynPT4pDb",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 455
},
"outputId": "f1f10293-4951-4e63-a77d-24f8b481491a"
},
"execution_count": 8,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" PM1.0_CF1_ug/m3 PM2.5_CF1_ug/m3 PM10.0_CF1_ug/m3 \\\n",
"created_at \n",
"2021-01-01 00:01:14+00:00 48.24 72.73 83.95 \n",
"2021-01-01 00:03:14+00:00 48.18 72.32 81.34 \n",
"2021-01-01 00:05:14+00:00 48.95 74.23 83.46 \n",
"2021-01-01 00:07:14+00:00 47.47 73.09 82.78 \n",
"2021-01-01 00:09:14+00:00 48.09 72.57 82.44 \n",
"... ... ... ... \n",
"2021-12-31 23:50:51+00:00 52.54 70.86 88.53 \n",
"2021-12-31 23:52:51+00:00 53.40 72.86 90.23 \n",
"2021-12-31 23:54:51+00:00 51.96 70.60 87.96 \n",
"2021-12-31 23:56:49+00:00 53.50 71.91 85.33 \n",
"2021-12-31 23:58:50+00:00 52.23 71.63 90.40 \n",
"\n",
" Temperature_F Humidity_% \n",
"created_at \n",
"2021-01-01 00:01:14+00:00 78.0 59.0 \n",
"2021-01-01 00:03:14+00:00 78.0 59.0 \n",
"2021-01-01 00:05:14+00:00 78.0 59.0 \n",
"2021-01-01 00:07:14+00:00 78.0 59.0 \n",
"2021-01-01 00:09:14+00:00 78.0 58.0 \n",
"... ... ... \n",
"2021-12-31 23:50:51+00:00 82.0 55.0 \n",
"2021-12-31 23:52:51+00:00 82.0 55.0 \n",
"2021-12-31 23:54:51+00:00 82.0 55.0 \n",
"2021-12-31 23:56:49+00:00 82.0 55.0 \n",
"2021-12-31 23:58:50+00:00 82.0 55.0 \n",
"\n",
"[236400 rows x 5 columns]"
],
"text/html": [
"\n",
" <div id=\"df-97a5439d-9038-46a5-b7b0-e7a3b8f4d8d0\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PM1.0_CF1_ug/m3</th>\n",
" <th>PM2.5_CF1_ug/m3</th>\n",
" <th>PM10.0_CF1_ug/m3</th>\n",
" <th>Temperature_F</th>\n",
" <th>Humidity_%</th>\n",
" </tr>\n",
" <tr>\n",
" <th>created_at</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2021-01-01 00:01:14+00:00</th>\n",
" <td>48.24</td>\n",
" <td>72.73</td>\n",
" <td>83.95</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:03:14+00:00</th>\n",
" <td>48.18</td>\n",
" <td>72.32</td>\n",
" <td>81.34</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:05:14+00:00</th>\n",
" <td>48.95</td>\n",
" <td>74.23</td>\n",
" <td>83.46</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:07:14+00:00</th>\n",
" <td>47.47</td>\n",
" <td>73.09</td>\n",
" <td>82.78</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:09:14+00:00</th>\n",
" <td>48.09</td>\n",
" <td>72.57</td>\n",
" <td>82.44</td>\n",
" <td>78.0</td>\n",
" <td>58.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:50:51+00:00</th>\n",
" <td>52.54</td>\n",
" <td>70.86</td>\n",
" <td>88.53</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:52:51+00:00</th>\n",
" <td>53.40</td>\n",
" <td>72.86</td>\n",
" <td>90.23</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:54:51+00:00</th>\n",
" <td>51.96</td>\n",
" <td>70.60</td>\n",
" <td>87.96</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:56:49+00:00</th>\n",
" <td>53.50</td>\n",
" <td>71.91</td>\n",
" <td>85.33</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:58:50+00:00</th>\n",
" <td>52.23</td>\n",
" <td>71.63</td>\n",
" <td>90.40</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>236400 rows × 5 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-97a5439d-9038-46a5-b7b0-e7a3b8f4d8d0')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-97a5439d-9038-46a5-b7b0-e7a3b8f4d8d0 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-97a5439d-9038-46a5-b7b0-e7a3b8f4d8d0');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 8
}
]
},
{
"cell_type": "code",
"source": [
"# We can create new columns dynamically\n",
"\n",
"xx['Month'] = xx.index.month\n",
"xx['Day'] = xx.index.day\n",
"xx"
],
"metadata": {
"id": "xWX514Mi44P8",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 455
},
"outputId": "1c02542b-15a4-4eb5-e284-d255c577073d"
},
"execution_count": 9,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" PM1.0_CF1_ug/m3 PM2.5_CF1_ug/m3 PM10.0_CF1_ug/m3 \\\n",
"created_at \n",
"2021-01-01 00:01:14+00:00 48.24 72.73 83.95 \n",
"2021-01-01 00:03:14+00:00 48.18 72.32 81.34 \n",
"2021-01-01 00:05:14+00:00 48.95 74.23 83.46 \n",
"2021-01-01 00:07:14+00:00 47.47 73.09 82.78 \n",
"2021-01-01 00:09:14+00:00 48.09 72.57 82.44 \n",
"... ... ... ... \n",
"2021-12-31 23:50:51+00:00 52.54 70.86 88.53 \n",
"2021-12-31 23:52:51+00:00 53.40 72.86 90.23 \n",
"2021-12-31 23:54:51+00:00 51.96 70.60 87.96 \n",
"2021-12-31 23:56:49+00:00 53.50 71.91 85.33 \n",
"2021-12-31 23:58:50+00:00 52.23 71.63 90.40 \n",
"\n",
" Temperature_F Humidity_% Month Day \n",
"created_at \n",
"2021-01-01 00:01:14+00:00 78.0 59.0 1 1 \n",
"2021-01-01 00:03:14+00:00 78.0 59.0 1 1 \n",
"2021-01-01 00:05:14+00:00 78.0 59.0 1 1 \n",
"2021-01-01 00:07:14+00:00 78.0 59.0 1 1 \n",
"2021-01-01 00:09:14+00:00 78.0 58.0 1 1 \n",
"... ... ... ... ... \n",
"2021-12-31 23:50:51+00:00 82.0 55.0 12 31 \n",
"2021-12-31 23:52:51+00:00 82.0 55.0 12 31 \n",
"2021-12-31 23:54:51+00:00 82.0 55.0 12 31 \n",
"2021-12-31 23:56:49+00:00 82.0 55.0 12 31 \n",
"2021-12-31 23:58:50+00:00 82.0 55.0 12 31 \n",
"\n",
"[236400 rows x 7 columns]"
],
"text/html": [
"\n",
" <div id=\"df-1cd54bc5-9c57-430d-b2e2-6592eb42c388\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PM1.0_CF1_ug/m3</th>\n",
" <th>PM2.5_CF1_ug/m3</th>\n",
" <th>PM10.0_CF1_ug/m3</th>\n",
" <th>Temperature_F</th>\n",
" <th>Humidity_%</th>\n",
" <th>Month</th>\n",
" <th>Day</th>\n",
" </tr>\n",
" <tr>\n",
" <th>created_at</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2021-01-01 00:01:14+00:00</th>\n",
" <td>48.24</td>\n",
" <td>72.73</td>\n",
" <td>83.95</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:03:14+00:00</th>\n",
" <td>48.18</td>\n",
" <td>72.32</td>\n",
" <td>81.34</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:05:14+00:00</th>\n",
" <td>48.95</td>\n",
" <td>74.23</td>\n",
" <td>83.46</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:07:14+00:00</th>\n",
" <td>47.47</td>\n",
" <td>73.09</td>\n",
" <td>82.78</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:09:14+00:00</th>\n",
" <td>48.09</td>\n",
" <td>72.57</td>\n",
" <td>82.44</td>\n",
" <td>78.0</td>\n",
" <td>58.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:50:51+00:00</th>\n",
" <td>52.54</td>\n",
" <td>70.86</td>\n",
" <td>88.53</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:52:51+00:00</th>\n",
" <td>53.40</td>\n",
" <td>72.86</td>\n",
" <td>90.23</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:54:51+00:00</th>\n",
" <td>51.96</td>\n",
" <td>70.60</td>\n",
" <td>87.96</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:56:49+00:00</th>\n",
" <td>53.50</td>\n",
" <td>71.91</td>\n",
" <td>85.33</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:58:50+00:00</th>\n",
" <td>52.23</td>\n",
" <td>71.63</td>\n",
" <td>90.40</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>236400 rows × 7 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1cd54bc5-9c57-430d-b2e2-6592eb42c388')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-1cd54bc5-9c57-430d-b2e2-6592eb42c388 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-1cd54bc5-9c57-430d-b2e2-6592eb42c388');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 9
}
]
},
{
"cell_type": "code",
"source": [
"# Basic statistics can also be performed smoothly\n",
"\n",
"# Get summary statistics for each column\n",
"xx.describe()\n",
"\n",
"xx.mean()\n",
"xx.mad()\n",
"xx.median()\n",
"xx.mode()\n",
"xx.skew()\n",
"xx.kurtosis()\n",
"xx.mean(),xx.mad(),xx.median(),xx.mode(),xx.skew(),xx.kurtosis()\n",
"\n"
],
"metadata": {
"id": "Fcrf8XFa5dUD",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "4b5c06f5-6da5-4810-992e-abca99e7d7f5"
},
"execution_count": 16,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(PM1.0_CF1_ug/m3 107.685950\n",
" PM2.5_CF1_ug/m3 119.071943\n",
" PM10.0_CF1_ug/m3 129.663154\n",
" Temperature_F 86.980960\n",
" Humidity_% 54.366760\n",
" Month 6.500212\n",
" Day 15.771252\n",
" dtype: float64, PM1.0_CF1_ug/m3 164.427646\n",
" PM2.5_CF1_ug/m3 165.437523\n",
" PM10.0_CF1_ug/m3 166.672929\n",
" Temperature_F 6.607736\n",
" Humidity_% 12.266818\n",
" Month 2.960459\n",
" Day 7.699652\n",
" dtype: float64, PM1.0_CF1_ug/m3 18.93\n",
" PM2.5_CF1_ug/m3 26.92\n",
" PM10.0_CF1_ug/m3 35.71\n",
" Temperature_F 84.00\n",
" Humidity_% 59.00\n",
" Month 7.00\n",
" Day 15.00\n",
" dtype: float64, PM1.0_CF1_ug/m3 PM2.5_CF1_ug/m3 PM10.0_CF1_ug/m3 Temperature_F \\\n",
" 0 5000.0 5000.0 5000.0 80.0 \n",
" \n",
" Humidity_% Month Day \n",
" 0 68.0 7 5 , PM1.0_CF1_ug/m3 7.519678\n",
" PM2.5_CF1_ug/m3 7.503632\n",
" PM10.0_CF1_ug/m3 7.488425\n",
" Temperature_F 1.070529\n",
" Humidity_% -1.122335\n",
" Month -0.007811\n",
" Day 0.030521\n",
" dtype: float64, PM1.0_CF1_ug/m3 54.637253\n",
" PM2.5_CF1_ug/m3 54.475155\n",
" PM10.0_CF1_ug/m3 54.324858\n",
" Temperature_F 0.543676\n",
" Humidity_% 0.489112\n",
" Month -1.181449\n",
" Day -1.218249\n",
" dtype: float64)"
]
},
"metadata": {},
"execution_count": 16
}
]
},
{
"cell_type": "code",
"source": [
"# we can do monthly or daily averages \n",
"\n",
"xx.groupby('Month').mean()\n",
"xx.groupby('Day').mean()"
],
"metadata": {
"id": "0hqTWJkF81Zu",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 457
},
"outputId": "e8d7dea3-6def-4d62-bebc-26f79dc37ba2"
},
"execution_count": 17,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" PM1.0_CF1_ug/m3 PM2.5_CF1_ug/m3 PM10.0_CF1_ug/m3 Temperature_F \\\n",
"Month \n",
"1 52.276437 79.875940 93.853704 88.454873 \n",
"2 51.066424 76.923989 99.504646 90.912020 \n",
"3 1114.960584 1127.326829 1142.863275 89.872522 \n",
"4 18.236530 26.182053 36.005899 88.762257 \n",
"5 14.353305 19.507145 24.503743 87.135596 \n",
"6 12.505217 17.808545 22.558042 84.671753 \n",
"7 18.694229 27.002339 35.139857 82.984570 \n",
"8 17.239346 25.230213 32.308245 82.915704 \n",
"9 8.881190 12.896085 16.461239 84.886832 \n",
"10 13.886377 19.205988 23.957939 86.263384 \n",
"11 18.620175 25.950085 33.284967 88.532043 \n",
"12 37.414530 57.309493 82.902907 89.263406 \n",
"\n",
" Humidity_% Day \n",
"Month \n",
"1 45.405447 16.120890 \n",
"2 40.089122 15.005654 \n",
"3 50.730837 16.528084 \n",
"4 52.916646 15.460072 \n",
"5 58.083199 15.293521 \n",
"6 59.938236 14.885949 \n",
"7 61.146678 15.828791 \n",
"8 63.646692 15.933271 \n",
"9 60.433289 15.061173 \n",
"10 58.993401 17.501119 \n",
"11 56.054700 15.504326 \n",
"12 43.219723 16.365054 "
],
"text/html": [
"\n",
" <div id=\"df-9888962b-e190-47e9-ad46-284f4227f8b3\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PM1.0_CF1_ug/m3</th>\n",
" <th>PM2.5_CF1_ug/m3</th>\n",
" <th>PM10.0_CF1_ug/m3</th>\n",
" <th>Temperature_F</th>\n",
" <th>Humidity_%</th>\n",
" <th>Day</th>\n",
" </tr>\n",
" <tr>\n",
" <th>Month</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>52.276437</td>\n",
" <td>79.875940</td>\n",
" <td>93.853704</td>\n",
" <td>88.454873</td>\n",
" <td>45.405447</td>\n",
" <td>16.120890</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>51.066424</td>\n",
" <td>76.923989</td>\n",
" <td>99.504646</td>\n",
" <td>90.912020</td>\n",
" <td>40.089122</td>\n",
" <td>15.005654</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1114.960584</td>\n",
" <td>1127.326829</td>\n",
" <td>1142.863275</td>\n",
" <td>89.872522</td>\n",
" <td>50.730837</td>\n",
" <td>16.528084</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>18.236530</td>\n",
" <td>26.182053</td>\n",
" <td>36.005899</td>\n",
" <td>88.762257</td>\n",
" <td>52.916646</td>\n",
" <td>15.460072</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>14.353305</td>\n",
" <td>19.507145</td>\n",
" <td>24.503743</td>\n",
" <td>87.135596</td>\n",
" <td>58.083199</td>\n",
" <td>15.293521</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>12.505217</td>\n",
" <td>17.808545</td>\n",
" <td>22.558042</td>\n",
" <td>84.671753</td>\n",
" <td>59.938236</td>\n",
" <td>14.885949</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>18.694229</td>\n",
" <td>27.002339</td>\n",
" <td>35.139857</td>\n",
" <td>82.984570</td>\n",
" <td>61.146678</td>\n",
" <td>15.828791</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>17.239346</td>\n",
" <td>25.230213</td>\n",
" <td>32.308245</td>\n",
" <td>82.915704</td>\n",
" <td>63.646692</td>\n",
" <td>15.933271</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>8.881190</td>\n",
" <td>12.896085</td>\n",
" <td>16.461239</td>\n",
" <td>84.886832</td>\n",
" <td>60.433289</td>\n",
" <td>15.061173</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>13.886377</td>\n",
" <td>19.205988</td>\n",
" <td>23.957939</td>\n",
" <td>86.263384</td>\n",
" <td>58.993401</td>\n",
" <td>17.501119</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>18.620175</td>\n",
" <td>25.950085</td>\n",
" <td>33.284967</td>\n",
" <td>88.532043</td>\n",
" <td>56.054700</td>\n",
" <td>15.504326</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>37.414530</td>\n",
" <td>57.309493</td>\n",
" <td>82.902907</td>\n",
" <td>89.263406</td>\n",
" <td>43.219723</td>\n",
" <td>16.365054</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9888962b-e190-47e9-ad46-284f4227f8b3')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-9888962b-e190-47e9-ad46-284f4227f8b3 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-9888962b-e190-47e9-ad46-284f4227f8b3');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 17
}
]
},
{
"cell_type": "code",
"source": [
"# It is possible to select based on certain conditions\n",
"\n",
"tt = xx[xx['Month'].isin([4,5,6,7])]\n",
"tt"
],
"metadata": {
"id": "u3VuOO4t9YVS",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 455
},
"outputId": "c2069ecf-fb12-4e40-8f85-6102040ec711"
},
"execution_count": 18,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" PM1.0_CF1_ug/m3 PM2.5_CF1_ug/m3 PM10.0_CF1_ug/m3 \\\n",
"created_at \n",
"2021-04-01 00:00:07+00:00 20.05 34.56 60.13 \n",
"2021-04-01 00:02:05+00:00 19.59 35.88 66.55 \n",
"2021-04-01 00:06:05+00:00 19.03 33.72 60.10 \n",
"2021-04-01 00:08:05+00:00 19.23 33.85 60.91 \n",
"2021-04-01 00:10:05+00:00 19.00 33.26 59.07 \n",
"... ... ... ... \n",
"2021-07-31 23:50:15+00:00 20.75 31.51 43.38 \n",
"2021-07-31 23:52:15+00:00 21.41 30.87 45.65 \n",
"2021-07-31 23:54:15+00:00 21.45 31.11 43.47 \n",
"2021-07-31 23:56:15+00:00 21.77 30.70 37.25 \n",
"2021-07-31 23:58:15+00:00 22.06 31.92 40.17 \n",
"\n",
" Temperature_F Humidity_% Month Day \n",
"created_at \n",
"2021-04-01 00:00:07+00:00 85.0 66.0 4 1 \n",
"2021-04-01 00:02:05+00:00 85.0 66.0 4 1 \n",
"2021-04-01 00:06:05+00:00 85.0 65.0 4 1 \n",
"2021-04-01 00:08:05+00:00 85.0 65.0 4 1 \n",
"2021-04-01 00:10:05+00:00 85.0 65.0 4 1 \n",
"... ... ... ... ... \n",
"2021-07-31 23:50:15+00:00 80.0 69.0 7 31 \n",
"2021-07-31 23:52:15+00:00 80.0 69.0 7 31 \n",
"2021-07-31 23:54:15+00:00 80.0 69.0 7 31 \n",
"2021-07-31 23:56:15+00:00 80.0 69.0 7 31 \n",
"2021-07-31 23:58:15+00:00 80.0 69.0 7 31 \n",
"\n",
"[80992 rows x 7 columns]"
],
"text/html": [
"\n",
" <div id=\"df-e6d45514-6972-4403-892d-34a88b7acf1c\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PM1.0_CF1_ug/m3</th>\n",
" <th>PM2.5_CF1_ug/m3</th>\n",
" <th>PM10.0_CF1_ug/m3</th>\n",
" <th>Temperature_F</th>\n",
" <th>Humidity_%</th>\n",
" <th>Month</th>\n",
" <th>Day</th>\n",
" </tr>\n",
" <tr>\n",
" <th>created_at</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2021-04-01 00:00:07+00:00</th>\n",
" <td>20.05</td>\n",
" <td>34.56</td>\n",
" <td>60.13</td>\n",
" <td>85.0</td>\n",
" <td>66.0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-04-01 00:02:05+00:00</th>\n",
" <td>19.59</td>\n",
" <td>35.88</td>\n",
" <td>66.55</td>\n",
" <td>85.0</td>\n",
" <td>66.0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-04-01 00:06:05+00:00</th>\n",
" <td>19.03</td>\n",
" <td>33.72</td>\n",
" <td>60.10</td>\n",
" <td>85.0</td>\n",
" <td>65.0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-04-01 00:08:05+00:00</th>\n",
" <td>19.23</td>\n",
" <td>33.85</td>\n",
" <td>60.91</td>\n",
" <td>85.0</td>\n",
" <td>65.0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-04-01 00:10:05+00:00</th>\n",
" <td>19.00</td>\n",
" <td>33.26</td>\n",
" <td>59.07</td>\n",
" <td>85.0</td>\n",
" <td>65.0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-07-31 23:50:15+00:00</th>\n",
" <td>20.75</td>\n",
" <td>31.51</td>\n",
" <td>43.38</td>\n",
" <td>80.0</td>\n",
" <td>69.0</td>\n",
" <td>7</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-07-31 23:52:15+00:00</th>\n",
" <td>21.41</td>\n",
" <td>30.87</td>\n",
" <td>45.65</td>\n",
" <td>80.0</td>\n",
" <td>69.0</td>\n",
" <td>7</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-07-31 23:54:15+00:00</th>\n",
" <td>21.45</td>\n",
" <td>31.11</td>\n",
" <td>43.47</td>\n",
" <td>80.0</td>\n",
" <td>69.0</td>\n",
" <td>7</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-07-31 23:56:15+00:00</th>\n",
" <td>21.77</td>\n",
" <td>30.70</td>\n",
" <td>37.25</td>\n",
" <td>80.0</td>\n",
" <td>69.0</td>\n",
" <td>7</td>\n",
" <td>31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-07-31 23:58:15+00:00</th>\n",
" <td>22.06</td>\n",
" <td>31.92</td>\n",
" <td>40.17</td>\n",
" <td>80.0</td>\n",
" <td>69.0</td>\n",
" <td>7</td>\n",
" <td>31</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>80992 rows × 7 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e6d45514-6972-4403-892d-34a88b7acf1c')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-e6d45514-6972-4403-892d-34a88b7acf1c button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-e6d45514-6972-4403-892d-34a88b7acf1c');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"source": [
"# Can we do something like a classification for good and bad air quality?\n",
"\n",
"xx.loc[xx['PM2.5_CF1_ug/m3']<50,'Quality'] = 'Good'\n",
"xx.loc[xx['PM2.5_CF1_ug/m3'].between(51,100),'Quality'] = 'Moderate'\n",
"xx.loc[xx['PM2.5_CF1_ug/m3'].between(101,150),'Quality'] = 'Sensitive'\n",
"xx.loc[xx['PM2.5_CF1_ug/m3'].between(151,200),'Quality'] = 'Highly sensitive'\n",
"xx.loc[xx['PM2.5_CF1_ug/m3'].between(201,300),'Quality'] = 'Dangerous'\n",
"xx.loc[xx['PM2.5_CF1_ug/m3']>300,'Quality'] = 'Terrible'\n",
"xx"
],
"metadata": {
"id": "00pxV22v9vwz",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 455
},
"outputId": "129d72ae-5962-4239-f385-834be4075661"
},
"execution_count": 19,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" PM1.0_CF1_ug/m3 PM2.5_CF1_ug/m3 PM10.0_CF1_ug/m3 \\\n",
"created_at \n",
"2021-01-01 00:01:14+00:00 48.24 72.73 83.95 \n",
"2021-01-01 00:03:14+00:00 48.18 72.32 81.34 \n",
"2021-01-01 00:05:14+00:00 48.95 74.23 83.46 \n",
"2021-01-01 00:07:14+00:00 47.47 73.09 82.78 \n",
"2021-01-01 00:09:14+00:00 48.09 72.57 82.44 \n",
"... ... ... ... \n",
"2021-12-31 23:50:51+00:00 52.54 70.86 88.53 \n",
"2021-12-31 23:52:51+00:00 53.40 72.86 90.23 \n",
"2021-12-31 23:54:51+00:00 51.96 70.60 87.96 \n",
"2021-12-31 23:56:49+00:00 53.50 71.91 85.33 \n",
"2021-12-31 23:58:50+00:00 52.23 71.63 90.40 \n",
"\n",
" Temperature_F Humidity_% Month Day Quality \n",
"created_at \n",
"2021-01-01 00:01:14+00:00 78.0 59.0 1 1 Moderate \n",
"2021-01-01 00:03:14+00:00 78.0 59.0 1 1 Moderate \n",
"2021-01-01 00:05:14+00:00 78.0 59.0 1 1 Moderate \n",
"2021-01-01 00:07:14+00:00 78.0 59.0 1 1 Moderate \n",
"2021-01-01 00:09:14+00:00 78.0 58.0 1 1 Moderate \n",
"... ... ... ... ... ... \n",
"2021-12-31 23:50:51+00:00 82.0 55.0 12 31 Moderate \n",
"2021-12-31 23:52:51+00:00 82.0 55.0 12 31 Moderate \n",
"2021-12-31 23:54:51+00:00 82.0 55.0 12 31 Moderate \n",
"2021-12-31 23:56:49+00:00 82.0 55.0 12 31 Moderate \n",
"2021-12-31 23:58:50+00:00 82.0 55.0 12 31 Moderate \n",
"\n",
"[236400 rows x 8 columns]"
],
"text/html": [
"\n",
" <div id=\"df-cc9d21f2-6949-4696-9683-1b84c3e0728c\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PM1.0_CF1_ug/m3</th>\n",
" <th>PM2.5_CF1_ug/m3</th>\n",
" <th>PM10.0_CF1_ug/m3</th>\n",
" <th>Temperature_F</th>\n",
" <th>Humidity_%</th>\n",
" <th>Month</th>\n",
" <th>Day</th>\n",
" <th>Quality</th>\n",
" </tr>\n",
" <tr>\n",
" <th>created_at</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2021-01-01 00:01:14+00:00</th>\n",
" <td>48.24</td>\n",
" <td>72.73</td>\n",
" <td>83.95</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:03:14+00:00</th>\n",
" <td>48.18</td>\n",
" <td>72.32</td>\n",
" <td>81.34</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:05:14+00:00</th>\n",
" <td>48.95</td>\n",
" <td>74.23</td>\n",
" <td>83.46</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:07:14+00:00</th>\n",
" <td>47.47</td>\n",
" <td>73.09</td>\n",
" <td>82.78</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:09:14+00:00</th>\n",
" <td>48.09</td>\n",
" <td>72.57</td>\n",
" <td>82.44</td>\n",
" <td>78.0</td>\n",
" <td>58.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:50:51+00:00</th>\n",
" <td>52.54</td>\n",
" <td>70.86</td>\n",
" <td>88.53</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:52:51+00:00</th>\n",
" <td>53.40</td>\n",
" <td>72.86</td>\n",
" <td>90.23</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:54:51+00:00</th>\n",
" <td>51.96</td>\n",
" <td>70.60</td>\n",
" <td>87.96</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:56:49+00:00</th>\n",
" <td>53.50</td>\n",
" <td>71.91</td>\n",
" <td>85.33</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:58:50+00:00</th>\n",
" <td>52.23</td>\n",
" <td>71.63</td>\n",
" <td>90.40</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>236400 rows × 8 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-cc9d21f2-6949-4696-9683-1b84c3e0728c')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-cc9d21f2-6949-4696-9683-1b84c3e0728c button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-cc9d21f2-6949-4696-9683-1b84c3e0728c');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 19
}
]
},
{
"cell_type": "code",
"source": [
"# Yes, pandas can change from 2 minutes data to any frequency\n",
"\n",
"xx.resample('H').mean()"
],
"metadata": {
"id": "6vH2UfhC-UA9",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 455
},
"outputId": "e12d9995-d178-450d-fe8f-386e2b087bb6"
},
"execution_count": 21,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" PM1.0_CF1_ug/m3 PM2.5_CF1_ug/m3 PM10.0_CF1_ug/m3 \\\n",
"created_at \n",
"2021-01-01 00:00:00+00:00 47.902000 72.259000 82.220000 \n",
"2021-01-01 01:00:00+00:00 53.006333 86.183667 110.456667 \n",
"2021-01-01 02:00:00+00:00 53.058000 88.314667 114.411667 \n",
"2021-01-01 03:00:00+00:00 51.493667 81.587333 99.405667 \n",
"2021-01-01 04:00:00+00:00 53.252667 82.738000 97.372333 \n",
"... ... ... ... \n",
"2021-12-31 19:00:00+00:00 50.453103 68.777241 87.038966 \n",
"2021-12-31 20:00:00+00:00 59.513333 81.695333 101.067000 \n",
"2021-12-31 21:00:00+00:00 57.508214 78.576786 97.284643 \n",
"2021-12-31 22:00:00+00:00 56.503667 77.536333 96.210667 \n",
"2021-12-31 23:00:00+00:00 54.125667 73.820000 91.576000 \n",
"\n",
" Temperature_F Humidity_% Month Day \n",
"created_at \n",
"2021-01-01 00:00:00+00:00 78.000000 59.166667 1.0 1.0 \n",
"2021-01-01 01:00:00+00:00 79.166667 62.433333 1.0 1.0 \n",
"2021-01-01 02:00:00+00:00 80.366667 62.900000 1.0 1.0 \n",
"2021-01-01 03:00:00+00:00 80.400000 63.800000 1.0 1.0 \n",
"2021-01-01 04:00:00+00:00 81.900000 63.833333 1.0 1.0 \n",
"... ... ... ... ... \n",
"2021-12-31 19:00:00+00:00 87.482759 46.551724 12.0 31.0 \n",
"2021-12-31 20:00:00+00:00 85.466667 49.966667 12.0 31.0 \n",
"2021-12-31 21:00:00+00:00 84.107143 52.428571 12.0 31.0 \n",
"2021-12-31 22:00:00+00:00 83.300000 53.566667 12.0 31.0 \n",
"2021-12-31 23:00:00+00:00 82.400000 54.400000 12.0 31.0 \n",
"\n",
"[8760 rows x 7 columns]"
],
"text/html": [
"\n",
" <div id=\"df-ebdf1ab4-a6ca-4c7b-8e25-863d3399f550\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PM1.0_CF1_ug/m3</th>\n",
" <th>PM2.5_CF1_ug/m3</th>\n",
" <th>PM10.0_CF1_ug/m3</th>\n",
" <th>Temperature_F</th>\n",
" <th>Humidity_%</th>\n",
" <th>Month</th>\n",
" <th>Day</th>\n",
" </tr>\n",
" <tr>\n",
" <th>created_at</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2021-01-01 00:00:00+00:00</th>\n",
" <td>47.902000</td>\n",
" <td>72.259000</td>\n",
" <td>82.220000</td>\n",
" <td>78.000000</td>\n",
" <td>59.166667</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 01:00:00+00:00</th>\n",
" <td>53.006333</td>\n",
" <td>86.183667</td>\n",
" <td>110.456667</td>\n",
" <td>79.166667</td>\n",
" <td>62.433333</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 02:00:00+00:00</th>\n",
" <td>53.058000</td>\n",
" <td>88.314667</td>\n",
" <td>114.411667</td>\n",
" <td>80.366667</td>\n",
" <td>62.900000</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 03:00:00+00:00</th>\n",
" <td>51.493667</td>\n",
" <td>81.587333</td>\n",
" <td>99.405667</td>\n",
" <td>80.400000</td>\n",
" <td>63.800000</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 04:00:00+00:00</th>\n",
" <td>53.252667</td>\n",
" <td>82.738000</td>\n",
" <td>97.372333</td>\n",
" <td>81.900000</td>\n",
" <td>63.833333</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 19:00:00+00:00</th>\n",
" <td>50.453103</td>\n",
" <td>68.777241</td>\n",
" <td>87.038966</td>\n",
" <td>87.482759</td>\n",
" <td>46.551724</td>\n",
" <td>12.0</td>\n",
" <td>31.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 20:00:00+00:00</th>\n",
" <td>59.513333</td>\n",
" <td>81.695333</td>\n",
" <td>101.067000</td>\n",
" <td>85.466667</td>\n",
" <td>49.966667</td>\n",
" <td>12.0</td>\n",
" <td>31.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 21:00:00+00:00</th>\n",
" <td>57.508214</td>\n",
" <td>78.576786</td>\n",
" <td>97.284643</td>\n",
" <td>84.107143</td>\n",
" <td>52.428571</td>\n",
" <td>12.0</td>\n",
" <td>31.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 22:00:00+00:00</th>\n",
" <td>56.503667</td>\n",
" <td>77.536333</td>\n",
" <td>96.210667</td>\n",
" <td>83.300000</td>\n",
" <td>53.566667</td>\n",
" <td>12.0</td>\n",
" <td>31.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:00:00+00:00</th>\n",
" <td>54.125667</td>\n",
" <td>73.820000</td>\n",
" <td>91.576000</td>\n",
" <td>82.400000</td>\n",
" <td>54.400000</td>\n",
" <td>12.0</td>\n",
" <td>31.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>8760 rows × 7 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ebdf1ab4-a6ca-4c7b-8e25-863d3399f550')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-ebdf1ab4-a6ca-4c7b-8e25-863d3399f550 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-ebdf1ab4-a6ca-4c7b-8e25-863d3399f550');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 21
}
]
},
{
"cell_type": "code",
"source": [
"# Missing values are a nightmare. Fortunately, we can use pandas to fill them\n",
"\n",
"xx.interpolate(method='spline',order=4)\n",
"\n",
"# you can get all the available methods here \n",
"# https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.interpolate.html#pandas.DataFrame.interpolate"
],
"metadata": {
"id": "JJxTMqjg_HeC",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 455
},
"outputId": "9c281734-816a-4465-bbf2-30332a209a7e"
},
"execution_count": 22,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" PM1.0_CF1_ug/m3 PM2.5_CF1_ug/m3 PM10.0_CF1_ug/m3 \\\n",
"created_at \n",
"2021-01-01 00:01:14+00:00 48.24 72.73 83.95 \n",
"2021-01-01 00:03:14+00:00 48.18 72.32 81.34 \n",
"2021-01-01 00:05:14+00:00 48.95 74.23 83.46 \n",
"2021-01-01 00:07:14+00:00 47.47 73.09 82.78 \n",
"2021-01-01 00:09:14+00:00 48.09 72.57 82.44 \n",
"... ... ... ... \n",
"2021-12-31 23:50:51+00:00 52.54 70.86 88.53 \n",
"2021-12-31 23:52:51+00:00 53.40 72.86 90.23 \n",
"2021-12-31 23:54:51+00:00 51.96 70.60 87.96 \n",
"2021-12-31 23:56:49+00:00 53.50 71.91 85.33 \n",
"2021-12-31 23:58:50+00:00 52.23 71.63 90.40 \n",
"\n",
" Temperature_F Humidity_% Month Day Quality \n",
"created_at \n",
"2021-01-01 00:01:14+00:00 78.0 59.0 1 1 Moderate \n",
"2021-01-01 00:03:14+00:00 78.0 59.0 1 1 Moderate \n",
"2021-01-01 00:05:14+00:00 78.0 59.0 1 1 Moderate \n",
"2021-01-01 00:07:14+00:00 78.0 59.0 1 1 Moderate \n",
"2021-01-01 00:09:14+00:00 78.0 58.0 1 1 Moderate \n",
"... ... ... ... ... ... \n",
"2021-12-31 23:50:51+00:00 82.0 55.0 12 31 Moderate \n",
"2021-12-31 23:52:51+00:00 82.0 55.0 12 31 Moderate \n",
"2021-12-31 23:54:51+00:00 82.0 55.0 12 31 Moderate \n",
"2021-12-31 23:56:49+00:00 82.0 55.0 12 31 Moderate \n",
"2021-12-31 23:58:50+00:00 82.0 55.0 12 31 Moderate \n",
"\n",
"[236400 rows x 8 columns]"
],
"text/html": [
"\n",
" <div id=\"df-dcf5cb7a-752c-47d9-bc3f-24e2384fe5b8\">\n",
" <div class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PM1.0_CF1_ug/m3</th>\n",
" <th>PM2.5_CF1_ug/m3</th>\n",
" <th>PM10.0_CF1_ug/m3</th>\n",
" <th>Temperature_F</th>\n",
" <th>Humidity_%</th>\n",
" <th>Month</th>\n",
" <th>Day</th>\n",
" <th>Quality</th>\n",
" </tr>\n",
" <tr>\n",
" <th>created_at</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2021-01-01 00:01:14+00:00</th>\n",
" <td>48.24</td>\n",
" <td>72.73</td>\n",
" <td>83.95</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:03:14+00:00</th>\n",
" <td>48.18</td>\n",
" <td>72.32</td>\n",
" <td>81.34</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:05:14+00:00</th>\n",
" <td>48.95</td>\n",
" <td>74.23</td>\n",
" <td>83.46</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:07:14+00:00</th>\n",
" <td>47.47</td>\n",
" <td>73.09</td>\n",
" <td>82.78</td>\n",
" <td>78.0</td>\n",
" <td>59.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-01-01 00:09:14+00:00</th>\n",
" <td>48.09</td>\n",
" <td>72.57</td>\n",
" <td>82.44</td>\n",
" <td>78.0</td>\n",
" <td>58.0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:50:51+00:00</th>\n",
" <td>52.54</td>\n",
" <td>70.86</td>\n",
" <td>88.53</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:52:51+00:00</th>\n",
" <td>53.40</td>\n",
" <td>72.86</td>\n",
" <td>90.23</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:54:51+00:00</th>\n",
" <td>51.96</td>\n",
" <td>70.60</td>\n",
" <td>87.96</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:56:49+00:00</th>\n",
" <td>53.50</td>\n",
" <td>71.91</td>\n",
" <td>85.33</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2021-12-31 23:58:50+00:00</th>\n",
" <td>52.23</td>\n",
" <td>71.63</td>\n",
" <td>90.40</td>\n",
" <td>82.0</td>\n",
" <td>55.0</td>\n",
" <td>12</td>\n",
" <td>31</td>\n",
" <td>Moderate</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>236400 rows × 8 columns</p>\n",
"</div>\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-dcf5cb7a-752c-47d9-bc3f-24e2384fe5b8')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
" \n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
" <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
" </svg>\n",
" </button>\n",
" \n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" flex-wrap:wrap;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-dcf5cb7a-752c-47d9-bc3f-24e2384fe5b8 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-dcf5cb7a-752c-47d9-bc3f-24e2384fe5b8');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
" </div>\n",
" "
]
},
"metadata": {},
"execution_count": 22
}
]
},
{
"cell_type": "code",
"source": [
"# Let's convert our temperature from Fahreheit to Celcius\n",
"\n",
"# Method 1:\n",
"xx['Temperature_F'] = (xx['Temperature_F'] - 32)/1.8\n",
"xx\n",
"\n",
"xx = pd.read_csv('osogbo.csv',index_col='created_at',usecols=['created_at','PM1.0_CF1_ug/m3','PM2.5_CF1_ug/m3',\n",
" 'PM10.0_CF1_ug/m3','Temperature_F','Humidity_%'])\n",
"# method 2:\n",
"def f_to_c(v):\n",
" return (v-32)/1.8\n",
"\n",
"\n",
"xx['Temperature_F'].apply(f_to_c)\n",
"\n",
"# Method 3\n",
"xx = pd.read_csv('osogbo.csv',index_col='created_at',usecols=['created_at','PM1.0_CF1_ug/m3','PM2.5_CF1_ug/m3',\n",
" 'PM10.0_CF1_ug/m3','Temperature_F','Humidity_%'])\n",
"\n",
"xx['Temperature_F'] = xx['Temperature_F'].apply(lambda a : (a-32)/1.8)"
],
"metadata": {
"id": "-wGQpwZZAa4k"
},
"execution_count": 24,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# some simple plotting\n",
"xx.plot() # this plots all the column in one plot\n",
"xx.index = pd.DatetimeIndex(xx.index)\n",
"xx = xx.resample('D').mean()"
],
"metadata": {
"id": "A1UvWnyiCd_Q"
},
"execution_count": 26,
"outputs": []
},
{
"cell_type": "code",
"source": [
"xx.interpolate(method='spline',order=4)\n",
"xx.plot(subplots=True)"
],
"metadata": {
"id": "a8JWzi0eCgmj",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 346
},
"outputId": "ed0add0c-b18b-45e1-e82e-1894140c1fab"
},
"execution_count": 28,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([<Axes: xlabel='created_at'>, <Axes: xlabel='created_at'>,\n",
" <Axes: xlabel='created_at'>, <Axes: xlabel='created_at'>,\n",
" <Axes: xlabel='created_at'>], dtype=object)"
]
},
"metadata": {},
"execution_count": 28
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 432x288 with 5 Axes>"
],
"image/png": "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\n"
},
"metadata": {
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"source": [
"# some of the particulate matter have unusually high values. We can replace them\n",
"import numpy as np\n",
"\n",
"xx['PM1.0_CF1_ug/m3'][xx['PM1.0_CF1_ug/m3'] > 300] = np.nan \n",
"xx['PM2.5_CF1_ug/m3'][xx['PM2.5_CF1_ug/m3'] > 300] = np.nan \n",
"xx['PM10.0_CF1_ug/m3'][xx['PM10.0_CF1_ug/m3'] > 300] = np.nan \n",
"\n",
"# then plot again\n",
"xx.plot(subplots=True,legend=None)"
],
"metadata": {
"id": "Qts0GrCMDVkh",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 344
},
"outputId": "ad5a3158-d116-4958-99d5-8d6a360ec366"
},
"execution_count": 29,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"array([<Axes: xlabel='created_at'>, <Axes: xlabel='created_at'>,\n",
" <Axes: xlabel='created_at'>, <Axes: xlabel='created_at'>,\n",
" <Axes: xlabel='created_at'>], dtype=object)"
]
},
"metadata": {},
"execution_count": 29
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 432x288 with 5 Axes>"
],
"image/png": "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\n"
},
"metadata": {
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"source": [
"# lastly, after manipulation, we can export our dataframe to other formats including excel\n",
"\n",
"xx.to_numpy()"
],
"metadata": {
"id": "5-sISiohEsuQ"
},
"execution_count": null,
"outputs": []
}
]
}