From 3683b2a25447c740e88ec6de706672b11f521727 Mon Sep 17 00:00:00 2001 From: Barbara Reimao Date: Thu, 22 Aug 2024 10:09:01 -0300 Subject: [PATCH] Atividade casa semana 11 --- exercicios/para-casa/exercicio_casa.ipynb | 502 ++++++++++++++++++++++ 1 file changed, 502 insertions(+) create mode 100644 exercicios/para-casa/exercicio_casa.ipynb diff --git a/exercicios/para-casa/exercicio_casa.ipynb b/exercicios/para-casa/exercicio_casa.ipynb new file mode 100644 index 0000000..425abd8 --- /dev/null +++ b/exercicios/para-casa/exercicio_casa.ipynb @@ -0,0 +1,502 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd \n", + "df = pd.read_csv('INMET SALVADOR 2023.csv', delimiter=';', skiprows=8, encoding='latin1')" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \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 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: 19Unnamed: 20Unnamed: 21
001/01/20230000 UTCNaN1010,51010,51010NaN25,523,325,9...23,288.086.088.0183.03,71,3NaNNaNNaN
101/01/20230100 UTCNaN1010,61010,61010,5NaN25,323,325,5...23,289.087.089.0189.03,61NaNNaNNaN
201/01/20230200 UTCNaN1010,61010,71010,6NaN2523,225,3...23,290.089.090.0191.04,51,1NaNNaNNaN
301/01/20230300 UTCNaN1010,11010,61010,1NaN24,923,225...23,191.089.090.0181.03,61,1NaNNaNNaN
401/01/20230400 UTCNaNNaNNaNNaNNaNNaNNaNNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "

5 rows × 22 columns

\n", + "
" + ], + "text/plain": [ + " Data Hora UTC PRECIPITAÇÃO TOTAL, HORÁRIO (mm) \\\n", + "0 01/01/2023 0000 UTC NaN \n", + "1 01/01/2023 0100 UTC NaN \n", + "2 01/01/2023 0200 UTC NaN \n", + "3 01/01/2023 0300 UTC NaN \n", + "4 01/01/2023 0400 UTC NaN \n", + "\n", + " PRESSAO ATMOSFERICA AO NIVEL DA ESTACAO, HORARIA (mB) \\\n", + "0 1010,5 \n", + "1 1010,6 \n", + "2 1010,6 \n", + "3 1010,1 \n", + "4 NaN \n", + "\n", + " PRESSÃO ATMOSFERICA MAX.NA HORA ANT. (AUT) (mB) \\\n", + "0 1010,5 \n", + "1 1010,6 \n", + "2 1010,7 \n", + "3 1010,6 \n", + "4 NaN \n", + "\n", + " PRESSÃO ATMOSFERICA MIN. NA HORA ANT. (AUT) (mB) RADIACAO GLOBAL (Kj/m²) \\\n", + "0 1010 NaN \n", + "1 1010,5 NaN \n", + "2 1010,6 NaN \n", + "3 1010,1 NaN \n", + "4 NaN NaN \n", + "\n", + " TEMPERATURA DO AR - BULBO SECO, HORARIA (°C) \\\n", + "0 25,5 \n", + "1 25,3 \n", + "2 25 \n", + "3 24,9 \n", + "4 NaN \n", + "\n", + " TEMPERATURA DO PONTO DE ORVALHO (°C) \\\n", + "0 23,3 \n", + "1 23,3 \n", + "2 23,2 \n", + "3 23,2 \n", + "4 NaN \n", + "\n", + " TEMPERATURA MÁXIMA NA HORA ANT. (AUT) (°C) ... \\\n", + "0 25,9 ... \n", + "1 25,5 ... \n", + "2 25,3 ... \n", + "3 25 ... \n", + "4 NaN ... \n", + "\n", + " TEMPERATURA ORVALHO MIN. NA HORA ANT. (AUT) (°C) \\\n", + "0 23,2 \n", + "1 23,2 \n", + "2 23,2 \n", + "3 23,1 \n", + "4 NaN \n", + "\n", + " UMIDADE REL. MAX. NA HORA ANT. (AUT) (%) \\\n", + "0 88.0 \n", + "1 89.0 \n", + "2 90.0 \n", + "3 91.0 \n", + "4 NaN \n", + "\n", + " UMIDADE REL. MIN. NA HORA ANT. (AUT) (%) \\\n", + "0 86.0 \n", + "1 87.0 \n", + "2 89.0 \n", + "3 89.0 \n", + "4 NaN \n", + "\n", + " UMIDADE RELATIVA DO AR, HORARIA (%) VENTO, DIREÇÃO HORARIA (gr) (° (gr)) \\\n", + "0 88.0 183.0 \n", + "1 89.0 189.0 \n", + "2 90.0 191.0 \n", + "3 90.0 181.0 \n", + "4 NaN NaN \n", + "\n", + " VENTO, RAJADA MAXIMA (m/s) VENTO, VELOCIDADE HORARIA (m/s) Unnamed: 19 \\\n", + "0 3,7 1,3 NaN \n", + "1 3,6 1 NaN \n", + "2 4,5 1,1 NaN \n", + "3 3,6 1,1 NaN \n", + "4 NaN NaN NaN \n", + "\n", + " Unnamed: 20 Unnamed: 21 \n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + "[5 rows x 22 columns]" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "np.float64(26.991666666666667)" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "coluna_temperatura = df['TEMPERATURA DO AR - BULBO SECO, HORARIA (°C)']\n", + "coluna_temperatura = pd.to_numeric(df['TEMPERATURA DO AR - BULBO SECO, HORARIA (°C)'], errors = 'coerce')\n", + "coluna_temperatura.mean()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df_radiacao_sem_nulo = df.dropna(subset = ['RADIACAO GLOBAL (Kj/m²)'])\n" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "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", + "
DataHora UTCTEMPERATURA DO AR - BULBO SECO, HORARIA (°C)
229606/04/20231600 UTCNaN
315612/05/20231200 UTCNaN
419124/06/20231500 UTCNaN
334020/05/20230400 UTCNaN
30613/01/20231800 UTC32
............
786824/11/20232000 UTC28
475918/07/20230700 UTCNaN
403418/06/20230200 UTCNaN
113817/02/20231000 UTCNaN
627919/09/20231500 UTCNaN
\n", + "

1000 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " Data Hora UTC TEMPERATURA DO AR - BULBO SECO, HORARIA (°C)\n", + "2296 06/04/2023 1600 UTC NaN\n", + "3156 12/05/2023 1200 UTC NaN\n", + "4191 24/06/2023 1500 UTC NaN\n", + "3340 20/05/2023 0400 UTC NaN\n", + "306 13/01/2023 1800 UTC 32\n", + "... ... ... ...\n", + "7868 24/11/2023 2000 UTC 28\n", + "4759 18/07/2023 0700 UTC NaN\n", + "4034 18/06/2023 0200 UTC NaN\n", + "1138 17/02/2023 1000 UTC NaN\n", + "6279 19/09/2023 1500 UTC NaN\n", + "\n", + "[1000 rows x 3 columns]" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_reduzido = df[['Data', 'Hora UTC', 'TEMPERATURA DO AR - BULBO SECO, HORARIA (°C)' ]]\n", + "df_reduzido.sample(n=1000)" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 0.781818\n", + "1 0.800000\n", + "2 0.818182\n", + "3 0.818182\n", + "4 NaN\n", + "Name: coluna_normalizada, dtype: float64" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df['coluna_normalizada'] = (df['UMIDADE RELATIVA DO AR, HORARIA (%)'] - df['UMIDADE RELATIVA DO AR, HORARIA (%)'].min())/ (df['UMIDADE RELATIVA DO AR, HORARIA (%)'].max() - df['UMIDADE RELATIVA DO AR, HORARIA (%)'].min())\n", + "\n", + "df['coluna_normalizada'].head()" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.4" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}