diff --git a/exercicios/para-casa/Exercicio_Casa_Raquel_Andrade.ipynb b/exercicios/para-casa/Exercicio_Casa_Raquel_Andrade.ipynb new file mode 100644 index 0000000..d0149fb --- /dev/null +++ b/exercicios/para-casa/Exercicio_Casa_Raquel_Andrade.ipynb @@ -0,0 +1,1286 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "qzFdP5YNQo_N" + }, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "source": [ + "df= pd.read_csv('recife-2021.CSV', delimiter=';', skiprows=8, encoding='latin1')" + ], + "metadata": { + "id": "v7vxpPSFQtyl" + }, + "execution_count": 4, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "df_reduzido = df.dropna(subset=['RADIACAO GLOBAL (Kj/m²)'])\n", + "df_reduzido" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 721 + }, + "id": "trLvOB-yQu60", + "outputId": "23134ace-668f-447d-9d5d-6b157f2839f1" + }, + "execution_count": 5, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Data Hora UTC PRECIPITAÇÃO TOTAL, HORÁRIO (mm) \\\n", + "9 2021/01/01 0900 UTC 0 \n", + "10 2021/01/01 1000 UTC 0 \n", + "11 2021/01/01 1100 UTC 0 \n", + "12 2021/01/01 1200 UTC 0 \n", + "13 2021/01/01 1300 UTC 0 \n", + "... ... ... ... \n", + "7553 2021/11/11 1700 UTC 0 \n", + "7554 2021/11/11 1800 UTC 0 \n", + "7555 2021/11/11 1900 UTC 0 \n", + "7556 2021/11/11 2000 UTC 0 \n", + "7557 2021/11/11 2100 UTC 0 \n", + "\n", + " PRESSAO ATMOSFERICA AO NIVEL DA ESTACAO, HORARIA (mB) \\\n", + "9 1013 \n", + "10 1013,3 \n", + "11 1013,5 \n", + "12 1013,6 \n", + "13 1013,6 \n", + "... ... \n", + "7553 1011,4 \n", + "7554 1011,1 \n", + "7555 1011 \n", + "7556 1011,2 \n", + "7557 1011,7 \n", + "\n", + " PRESSÃO ATMOSFERICA MAX.NA HORA ANT. (AUT) (mB) \\\n", + "9 1013 \n", + "10 1013,3 \n", + "11 1013,6 \n", + "12 1013,7 \n", + "13 1013,7 \n", + "... ... \n", + "7553 1011,8 \n", + "7554 1011,4 \n", + "7555 1011,1 \n", + "7556 1011,3 \n", + "7557 1011,7 \n", + "\n", + " PRESSÃO ATMOSFERICA MIN. NA HORA ANT. (AUT) (mB) RADIACAO GLOBAL (Kj/m²) \\\n", + "9 1012,6 114,6 \n", + "10 1013 762,2 \n", + "11 1013,3 1862,8 \n", + "12 1013,4 2543,3 \n", + "13 1013,5 3397,4 \n", + "... ... ... \n", + "7553 1011,4 2262,6 \n", + "7554 1011 1948,9 \n", + "7555 1010,9 1019,7 \n", + "7556 1011 287,3 \n", + "7557 1011,2 9 \n", + "\n", + " TEMPERATURA DO AR - BULBO SECO, HORARIA (°C) \\\n", + "9 25,1 \n", + "10 27,2 \n", + "11 28,8 \n", + "12 29,6 \n", + "13 30,3 \n", + "... ... \n", + "7553 30,3 \n", + "7554 29,4 \n", + "7555 28,6 \n", + "7556 27,4 \n", + "7557 26,8 \n", + "\n", + " TEMPERATURA DO PONTO DE ORVALHO (°C) \\\n", + "9 22,1 \n", + "10 21,4 \n", + "11 20,9 \n", + "12 21,4 \n", + "13 20,9 \n", + "... ... \n", + "7553 23 \n", + "7554 22,6 \n", + "7555 22,6 \n", + "7556 22,6 \n", + "7557 22,7 \n", + "\n", + " TEMPERATURA MÁXIMA NA HORA ANT. (AUT) (°C) \\\n", + "9 25,1 \n", + "10 27,5 \n", + "11 28,9 \n", + "12 29,6 \n", + "13 30,5 \n", + "... ... \n", + "7553 31,1 \n", + "7554 31 \n", + "7555 30 \n", + "7556 28,7 \n", + "7557 27,4 \n", + "\n", + " TEMPERATURA MÍNIMA NA HORA ANT. (AUT) (°C) \\\n", + "9 24,3 \n", + "10 25,1 \n", + "11 27,2 \n", + "12 28,7 \n", + "13 29,7 \n", + "... ... \n", + "7553 30,1 \n", + "7554 29,4 \n", + "7555 28,5 \n", + "7556 27,4 \n", + "7557 26,8 \n", + "\n", + " TEMPERATURA ORVALHO MAX. NA HORA ANT. (AUT) (°C) \\\n", + "9 22,1 \n", + "10 22,3 \n", + "11 22,3 \n", + "12 21,6 \n", + "13 21,5 \n", + "... ... \n", + "7553 23,7 \n", + "7554 23,4 \n", + "7555 23,3 \n", + "7556 22,7 \n", + "7557 22,8 \n", + "\n", + " TEMPERATURA ORVALHO MIN. NA HORA ANT. (AUT) (°C) \\\n", + "9 21,6 \n", + "10 21,2 \n", + "11 20,7 \n", + "12 20,4 \n", + "13 20,3 \n", + "... ... \n", + "7553 22,2 \n", + "7554 22,4 \n", + "7555 22,3 \n", + "7556 22,3 \n", + "7557 22,5 \n", + "\n", + " UMIDADE REL. MAX. NA HORA ANT. (AUT) (%) \\\n", + "9 86.0 \n", + "10 83.0 \n", + "11 72.0 \n", + "12 63.0 \n", + "13 61.0 \n", + "... ... \n", + "7553 66.0 \n", + "7554 68.0 \n", + "7555 72.0 \n", + "7556 75.0 \n", + "7557 79.0 \n", + "\n", + " UMIDADE REL. MIN. NA HORA ANT. (AUT) (%) \\\n", + "9 83.0 \n", + "10 69.0 \n", + "11 62.0 \n", + "12 59.0 \n", + "13 55.0 \n", + "... ... \n", + "7553 60.0 \n", + "7554 60.0 \n", + "7555 66.0 \n", + "7556 69.0 \n", + "7557 75.0 \n", + "\n", + " UMIDADE RELATIVA DO AR, HORARIA (%) \\\n", + "9 83.0 \n", + "10 71.0 \n", + "11 63.0 \n", + "12 61.0 \n", + "13 57.0 \n", + "... ... \n", + "7553 65.0 \n", + "7554 67.0 \n", + "7555 70.0 \n", + "7556 75.0 \n", + "7557 78.0 \n", + "\n", + " VENTO, DIREÇÃO HORARIA (gr) (° (gr)) VENTO, RAJADA MAXIMA (m/s) \\\n", + "9 116.0 3,5 \n", + "10 109.0 4,8 \n", + "11 124.0 5,1 \n", + "12 122.0 6,4 \n", + "13 131.0 6,5 \n", + "... ... ... \n", + "7553 121.0 6,5 \n", + "7554 118.0 6,2 \n", + "7555 129.0 6,2 \n", + "7556 107.0 5,8 \n", + "7557 120.0 4,9 \n", + "\n", + " VENTO, VELOCIDADE HORARIA (m/s) Unnamed: 19 \n", + "9 1,1 NaN \n", + "10 1,7 NaN \n", + "11 2,1 NaN \n", + "12 2,3 NaN \n", + "13 2,5 NaN \n", + "... ... ... \n", + "7553 2,5 NaN \n", + "7554 2,7 NaN \n", + "7555 2 NaN \n", + "7556 1,9 NaN \n", + "7557 1,6 NaN \n", + "\n", + "[4116 rows x 20 columns]" + ], + "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", + " \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", + " \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", + "
DataHora UTCPRECIPITAÇÃO TOTAL, HORÁRIO (mm)PRESSAO ATMOSFERICA AO NIVEL DA ESTACAO, HORARIA (mB)PRESSÃO ATMOSFERICA MAX.NA HORA ANT. (AUT) (mB)PRESSÃO ATMOSFERICA MIN. NA HORA ANT. (AUT) (mB)RADIACAO GLOBAL (Kj/m²)TEMPERATURA DO AR - BULBO SECO, HORARIA (°C)TEMPERATURA DO PONTO DE ORVALHO (°C)TEMPERATURA MÁXIMA NA HORA ANT. (AUT) (°C)TEMPERATURA MÍNIMA NA HORA ANT. (AUT) (°C)TEMPERATURA ORVALHO MAX. NA HORA ANT. (AUT) (°C)TEMPERATURA ORVALHO MIN. NA HORA ANT. (AUT) (°C)UMIDADE REL. MAX. NA HORA ANT. (AUT) (%)UMIDADE REL. MIN. NA HORA ANT. (AUT) (%)UMIDADE RELATIVA DO AR, HORARIA (%)VENTO, DIREÇÃO HORARIA (gr) (° (gr))VENTO, RAJADA MAXIMA (m/s)VENTO, VELOCIDADE HORARIA (m/s)Unnamed: 19
92021/01/010900 UTC0101310131012,6114,625,122,125,124,322,121,686.083.083.0116.03,51,1NaN
102021/01/011000 UTC01013,31013,31013762,227,221,427,525,122,321,283.069.071.0109.04,81,7NaN
112021/01/011100 UTC01013,51013,61013,31862,828,820,928,927,222,320,772.062.063.0124.05,12,1NaN
122021/01/011200 UTC01013,61013,71013,42543,329,621,429,628,721,620,463.059.061.0122.06,42,3NaN
132021/01/011300 UTC01013,61013,71013,53397,430,320,930,529,721,520,361.055.057.0131.06,52,5NaN
...............................................................
75532021/11/111700 UTC01011,41011,81011,42262,630,32331,130,123,722,266.060.065.0121.06,52,5NaN
75542021/11/111800 UTC01011,11011,410111948,929,422,63129,423,422,468.060.067.0118.06,22,7NaN
75552021/11/111900 UTC010111011,11010,91019,728,622,63028,523,322,372.066.070.0129.06,22NaN
75562021/11/112000 UTC01011,21011,31011287,327,422,628,727,422,722,375.069.075.0107.05,81,9NaN
75572021/11/112100 UTC01011,71011,71011,2926,822,727,426,822,822,579.075.078.0120.04,91,6NaN
\n", + "

4116 rows × 20 columns

\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" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "df_reduzido", + "repr_error": "0" + } + }, + "metadata": {}, + "execution_count": 5 + } + ] + }, + { + "cell_type": "code", + "source": [ + "nulos_antes = df['RADIACAO GLOBAL (Kj/m²)'].isnull().sum()\n", + "print(\"Quantidade de nulos antes da remoçao: \",nulos_antes)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "g6o9AOLVQ2-D", + "outputId": "9a40c39d-0317-409d-c43b-d78bef713d23" + }, + "execution_count": 6, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Quantidade de nulos antes da remoçao: 4644\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "nulos_depois = df_reduzido['RADIACAO GLOBAL (Kj/m²)'].isnull().sum()\n", + "print(\"Quantidade de nulos depois da remoçao: \",nulos_depois)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "DodcvjjLQ6FV", + "outputId": "1d8946b2-863b-43ed-e0cc-1b2948b7d434" + }, + "execution_count": 7, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Quantidade de nulos depois da remoçao: 0\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "df_reduzido = df[['Data', 'TEMPERATURA MÁXIMA NA HORA ANT. (AUT) (°C)', 'RADIACAO GLOBAL (Kj/m²)' ]].sample(n=1000)\n", + "df_reduzido.head(1000)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 424 + }, + "id": "tQk5-HE9Q839", + "outputId": "3f14acdd-d8b3-416b-a2a5-24394af70d41" + }, + "execution_count": 8, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Data TEMPERATURA MÁXIMA NA HORA ANT. (AUT) (°C) \\\n", + "8542 2021/12/22 NaN \n", + "3271 2021/05/17 22 \n", + "2545 2021/04/17 24,2 \n", + "6070 2021/09/10 25,1 \n", + "1714 2021/03/13 26,3 \n", + "... ... ... \n", + "5306 2021/08/10 22,2 \n", + "7967 2021/11/28 NaN \n", + "5394 2021/08/13 27,9 \n", + "294 2021/01/13 23,4 \n", + "7034 2021/10/21 26,6 \n", + "\n", + " RADIACAO GLOBAL (Kj/m²) \n", + "8542 NaN \n", + "3271 NaN \n", + "2545 NaN \n", + "6070 NaN \n", + "1714 393,4 \n", + "... ... \n", + "5306 NaN \n", + "7967 NaN \n", + "5394 2375,1 \n", + "294 NaN \n", + "7034 NaN \n", + "\n", + "[1000 rows x 3 columns]" + ], + "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", + "
DataTEMPERATURA MÁXIMA NA HORA ANT. (AUT) (°C)RADIACAO GLOBAL (Kj/m²)
85422021/12/22NaNNaN
32712021/05/1722NaN
25452021/04/1724,2NaN
60702021/09/1025,1NaN
17142021/03/1326,3393,4
............
53062021/08/1022,2NaN
79672021/11/28NaNNaN
53942021/08/1327,92375,1
2942021/01/1323,4NaN
70342021/10/2126,6NaN
\n", + "

1000 rows × 3 columns

\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "df_reduzido", + "repr_error": "0" + } + }, + "metadata": {}, + "execution_count": 8 + } + ] + }, + { + "cell_type": "code", + "source": [ + "df_reduzido['TEMPERATURA MÁXIMA NA HORA ANT. (AUT) (°C)'].dtype" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "aU596P_MRA-B", + "outputId": "e4223d3e-e30a-4a8f-d02e-f37593a79304" + }, + "execution_count": 9, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "dtype('O')" + ] + }, + "metadata": {}, + "execution_count": 9 + } + ] + }, + { + "cell_type": "code", + "source": [ + "df_reduzido = pd.to_numeric(df_reduzido['TEMPERATURA MÁXIMA NA HORA ANT. (AUT) (°C)'], errors='coerce')" + ], + "metadata": { + "id": "o7E3oMGLRD8K" + }, + "execution_count": 11, + "outputs": [] + } + ] +} \ No newline at end of file