{ "cells": [ { "cell_type": "markdown", "id": "a3a24fe8-7ae1-4402-87be-9166aa8fc380", "metadata": {}, "source": [ "# Calidad del dato\n", "## Caso Calidad del aire" ] }, { "cell_type": "code", "execution_count": 3, "id": "c0591590-8d32-49a1-948d-603ff42411ef", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "import warnings\n", "warnings.filterwarnings('ignore')\n", "\n", "pd.options.display.float_format = '{:.2f}'.format #Desactivar notación científica en pandas:\n", "np.set_printoptions(suppress=True) #Desactivar notación científica en numpy:\n", "pd.set_option('display.max_columns', None) #comando para mostrar todas las columnas" ] }, { "cell_type": "code", "execution_count": 4, "id": "a7092e2d-c45e-49ab-acdd-7765bcc69df4", "metadata": {}, "outputs": [], "source": [ "df1 = pd.read_csv(\"./datos/calidad_1.csv\", sep=\",\", decimal=\".\", encoding=\"WINDOWS-1252\")" ] }, { "cell_type": "code", "execution_count": 5, "id": "2329f64b-c44b-4da1-a37b-a26b9d207929", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
datewswdnoxno2o3pm10so2copm25
001/01/1998 00:000.60280.00285.0039.001.0029.004.723.37NaN
101/01/1998 01:002.16230.00NaNNaNNaN37.00NaNNaNNaN
201/01/1998 02:002.76190.00NaNNaN3.0034.006.839.60NaN
301/01/1998 03:002.16170.00493.0052.003.0035.007.6610.22NaN
401/01/1998 04:002.40180.00468.0078.002.0034.008.078.91NaN
\n", "
" ], "text/plain": [ " date ws wd nox no2 o3 pm10 so2 co pm25\n", "0 01/01/1998 00:00 0.60 280.00 285.00 39.00 1.00 29.00 4.72 3.37 NaN\n", "1 01/01/1998 01:00 2.16 230.00 NaN NaN NaN 37.00 NaN NaN NaN\n", "2 01/01/1998 02:00 2.76 190.00 NaN NaN 3.00 34.00 6.83 9.60 NaN\n", "3 01/01/1998 03:00 2.16 170.00 493.00 52.00 3.00 35.00 7.66 10.22 NaN\n", "4 01/01/1998 04:00 2.40 180.00 468.00 78.00 2.00 34.00 8.07 8.91 NaN" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df1.head()" ] }, { "cell_type": "code", "execution_count": 7, "id": "e50ed028-8edc-447b-99aa-0dcb8a76cd8d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 65533 entries, 0 to 65532\n", "Data columns (total 10 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 date 65533 non-null object \n", " 1 ws 64907 non-null float64\n", " 2 wd 65314 non-null float64\n", " 3 nox 63110 non-null float64\n", " 4 no2 63095 non-null float64\n", " 5 o3 62947 non-null float64\n", " 6 pm10 63372 non-null float64\n", " 7 so2 55499 non-null float64\n", " 8 co 63604 non-null float64\n", " 9 pm25 56759 non-null float64\n", "dtypes: float64(9), object(1)\n", "memory usage: 5.0+ MB\n" ] } ], "source": [ "df1.info()" ] }, { "cell_type": "code", "execution_count": 89, "id": "a12f9478-8c41-4829-9b14-acb3b57beac5", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
wswdnoxno2o3pm10so2copm25
count64907.0065314.0063110.0063095.0062947.0063372.0055499.0063604.0056759.00
mean4.49200.03178.8049.137.1234.384.751.4621.70
std2.4094.46121.5222.647.5420.473.651.1212.64
min-0.240.000.000.00-1.00-1.00-2.17-0.03-1.00
25%2.60140.0082.0033.002.0022.002.100.6313.00
50%4.10210.00153.0046.004.0031.004.001.1420.00
75%5.76270.00249.0061.0010.0044.006.501.9828.00
max20.16360.001144.00206.0070.00801.0063.2019.70398.00
\n", "
" ], "text/plain": [ " ws wd nox no2 o3 pm10 so2 co \\\n", "count 64907.00 65314.00 63110.00 63095.00 62947.00 63372.00 55499.00 63604.00 \n", "mean 4.49 200.03 178.80 49.13 7.12 34.38 4.75 1.46 \n", "std 2.40 94.46 121.52 22.64 7.54 20.47 3.65 1.12 \n", "min -0.24 0.00 0.00 0.00 -1.00 -1.00 -2.17 -0.03 \n", "25% 2.60 140.00 82.00 33.00 2.00 22.00 2.10 0.63 \n", "50% 4.10 210.00 153.00 46.00 4.00 31.00 4.00 1.14 \n", "75% 5.76 270.00 249.00 61.00 10.00 44.00 6.50 1.98 \n", "max 20.16 360.00 1144.00 206.00 70.00 801.00 63.20 19.70 \n", "\n", " pm25 \n", "count 56759.00 \n", "mean 21.70 \n", "std 12.64 \n", "min -1.00 \n", "25% 13.00 \n", "50% 20.00 \n", "75% 28.00 \n", "max 398.00 " ] }, "execution_count": 89, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df1.describe()" ] }, { "cell_type": "code", "execution_count": 90, "id": "78fed4b0-fcae-49f3-b73a-e788aad75e49", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "date 0\n", "ws 626\n", "wd 219\n", "nox 2423\n", "no2 2438\n", "o3 2586\n", "pm10 2161\n", "so2 10034\n", "co 1929\n", "pm25 8774\n", "dtype: int64" ] }, "execution_count": 90, "metadata": {}, "output_type": "execute_result" } ], "source": [ "#Tenemos valores perdidos, comprobamos por columna cuántos.\n", "df1.isnull().sum(axis=0)" ] }, { "cell_type": "code", "execution_count": 91, "id": "423fdad0-6280-451d-bb18-547639d3d241", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "date 0.00\n", "ws 0.01\n", "wd 0.00\n", "nox 0.04\n", "no2 0.04\n", "o3 0.04\n", "pm10 0.03\n", "so2 0.15\n", "co 0.03\n", "pm25 0.13\n", "dtype: float64" ] }, "execution_count": 91, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# ¿Qué porcentaje de valores perdidos tenemos por columna?\n", "df1.isnull().sum(axis=0)/df1.shape[0]" ] }, { "cell_type": "code", "execution_count": 92, "id": "c1e9535e-307b-4160-93c5-e47b2c3a1f8f", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "date object\n", "ws float64\n", "wd float64\n", "nox float64\n", "no2 float64\n", "o3 float64\n", "pm10 float64\n", "so2 float64\n", "co float64\n", "pm25 float64\n", "dtype: object" ] }, "execution_count": 92, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# ¿Qué formato tienen las variables? \n", "df1.dtypes" ] }, { "cell_type": "code", "execution_count": 97, "id": "de875d46-3541-4120-bdc6-f4eaaf990336", "metadata": {}, "outputs": [], "source": [ "# De momento la variable date, no tiene formato fecha. Lo modificamos.\n", "df1['date'] = pd.to_datetime(df1.date)" ] }, { "cell_type": "code", "execution_count": 98, "id": "23747d81-11d0-4e95-98d6-725e10686e9d", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "date datetime64[ns]\n", "ws float64\n", "wd float64\n", "nox float64\n", "no2 float64\n", "o3 float64\n", "pm10 float64\n", "so2 float64\n", "co float64\n", "pm25 float64\n", "dtype: object" ] }, "execution_count": 98, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df1.dtypes" ] }, { "cell_type": "code", "execution_count": 100, "id": "13117477-0dbd-4bb6-bcbc-65507576e71b", "metadata": {}, "outputs": [], "source": [ "# Enriquecemos el dataset, con nueva información\n", "df1['dia'] = df1.date.dt.day\n", "df1['mes'] = df1.date.dt.month\n", "df1['anio'] = df1.date.dt.year" ] }, { "cell_type": "code", "execution_count": 79, "id": "52e49e01-900c-4062-92f3-13e311ec2f7e", "metadata": {}, "outputs": [], "source": [ "#Reordenamos los datos\n", "df1 = df1.iloc[:,[0,-3,-2,-1,1,2,3,4,5,6,7,8,9]]" ] }, { "cell_type": "code", "execution_count": 80, "id": "4b4e9f94-c08d-47f7-8ed8-183b87d5f1c0", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['date', 'dia', 'mes', 'anio', 'ws', 'wd', 'nox', 'no2', 'o3', 'pm10',\n", " 'so2', 'co', 'pm25'],\n", " dtype='object')" ] }, "execution_count": 80, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df1.columns" ] }, { "cell_type": "code", "execution_count": 104, "id": "3a89935c-f926-400e-ac7c-f6c01326fe22", "metadata": {}, "outputs": [], "source": [ "# Los nombres son un poco crípticos. Lo solucionamos\n", "df1.columns = ['fecha', 'dia', 'mes', 'anio', 'velocidadviento', 'direccionviento', 'nox', 'no2', 'ozono', 'particulas10', 'so2', 'co', 'particulas25']" ] }, { "cell_type": "code", "execution_count": 105, "id": "85905b83-33df-4f0e-ae98-071127146ed5", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
fechadiamesaniovelocidadvientodireccionvientonoxno2ozonoparticulas10so2coparticulas25
01998-01-01 00:00:000.60280.00285.0039.001.0029.004.723.37NaN111998
11998-01-01 01:00:002.16230.00NaNNaNNaN37.00NaNNaNNaN111998
21998-01-01 02:00:002.76190.00NaNNaN3.0034.006.839.60NaN111998
31998-01-01 03:00:002.16170.00493.0052.003.0035.007.6610.22NaN111998
41998-01-01 04:00:002.40180.00468.0078.002.0034.008.078.91NaN111998
\n", "
" ], "text/plain": [ " fecha dia mes anio velocidadviento direccionviento \\\n", "0 1998-01-01 00:00:00 0.60 280.00 285.00 39.00 1.00 \n", "1 1998-01-01 01:00:00 2.16 230.00 NaN NaN NaN \n", "2 1998-01-01 02:00:00 2.76 190.00 NaN NaN 3.00 \n", "3 1998-01-01 03:00:00 2.16 170.00 493.00 52.00 3.00 \n", "4 1998-01-01 04:00:00 2.40 180.00 468.00 78.00 2.00 \n", "\n", " nox no2 ozono particulas10 so2 co particulas25 \n", "0 29.00 4.72 3.37 NaN 1 1 1998 \n", "1 37.00 NaN NaN NaN 1 1 1998 \n", "2 34.00 6.83 9.60 NaN 1 1 1998 \n", "3 35.00 7.66 10.22 NaN 1 1 1998 \n", "4 34.00 8.07 8.91 NaN 1 1 1998 " ] }, "execution_count": 105, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df1.head()" ] }, { "cell_type": "code", "execution_count": 125, "id": "60146a75-70b4-41d6-94e2-b9eb936cd401", "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Pintamos los datos para ver su distribución\n", "import matplotlib.pyplot as plt\n", "plt.plot(df1.fecha, df1.velocidadviento, 'o', color='blue')\n", "plt.title('Velocidad viento', fontsize=20)\n", "plt.xlabel('Fecha', fontsize=12)\n", "plt.ylabel('m/s', fontsize=12)\n", "plt.show()\n", "plt.plot(df1.fecha, df1.particulas10, 'v', color='red')\n", "plt.title('Partículas por millón', fontsize=20)\n", "plt.xlabel('Fecha', fontsize=12)\n", "plt.ylabel('pm10', fontsize=12)\n", "plt.show()\n", "plt.plot(df1.fecha, df1.so2, '2', color='green')\n", "plt.title('Dioxido azufre', fontsize=20)\n", "plt.xlabel('Fecha', fontsize=12)\n", "plt.ylabel('so2', fontsize=12)\n", "plt.show()\n" ] }, { "cell_type": "code", "execution_count": null, "id": "4180ccbc-92c1-434b-952d-b5227a9c87d9", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.8.12" } }, "nbformat": 4, "nbformat_minor": 5 }