{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Data Science Academy - Python Fundamentos - Capítulo 8\n", "\n", "## Download: http://github.com/dsacademybr" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercícios Sobre Módulos Python Para Análise de Dados" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### ****** ATENÇÃO ******\n", "### Alguns dos exercícios podem requerer pesquisa adicional na documentação dos pacotes. Pesquise!" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercício 1" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "CPU times: user 13.5 ms, sys: 4.26 ms, total: 17.8 ms\n", "Wall time: 17.9 ms\n", "CPU times: user 587 ms, sys: 169 ms, total: 756 ms\n", "Wall time: 757 ms\n" ] } ], "source": [ "# Crie um array NumPy com 1000000 e uma lista com 1000000.\n", "# Multiplique cada elemento do array e da lista por 2 e calcule o tempo de execução com cada um dos objetos (use %time).\n", "# Qual objeto oferece melhor performance, array NumPy ou lista?\n", "import numpy as np\n", "my_arr = np.arange(1000000)\n", "my_list = list(range(1000000))\n", "\n", "%time for _ in range(10): my_arr2 = my_arr * 2\n", "%time for _ in range(10): my_list2 = [x * 2 for x in my_list]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercício 2" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Exercício 2\n", "# Crie um array de 10 elementos\n", "# Altere o valores de todos os elementos dos índices 5 a 8 para 0\n", "import numpy as np\n", "arr = np.arange(10)\n", "arr" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 1, 2, 3, 4, 0, 0, 0, 8, 9])" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "arr[5:8] = 0\n", "arr" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercício 3" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[[ 1, 2, 3],\n", " [ 4, 5, 6]],\n", "\n", " [[ 7, 8, 9],\n", " [10, 11, 12]]])" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Crie um array de 3 dimensões e imprima a dimensão 1 \n", "import numpy as np\n", "arr3d = np.array([[[1, 2, 3], [4, 5, 6]], [[7, 8, 9], [10, 11, 12]]])\n", "arr3d" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[1, 2, 3],\n", " [4, 5, 6]])" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "arr3d[0]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercício 4" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[1, 2, 3],\n", " [4, 5, 6],\n", " [7, 8, 9]])" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Crie um array de duas dimensões (matriz).\n", "# Imprima os elementos da terceira linha da matriz\n", "# Imprima todos os elementos da primeira e segunda linhas e segunda e terceira colunas\n", "arr2d = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])\n", "arr2d" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([7, 8, 9])" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Imprima os elementos da terceira linha da matriz\n", "arr2d[2]" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[2, 3],\n", " [5, 6]])" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Imprima todos os elementos da primeira e segunda linhas e segunda e terceira colunas\n", "arr2d[:2, 1:]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercício 5" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 0, 1, 2, 3, 4],\n", " [ 5, 6, 7, 8, 9],\n", " [10, 11, 12, 13, 14]])" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Calcule a transposta da matriz abaixo\n", "arr = np.arange(15).reshape((3, 5))\n", "arr" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([[ 0, 5, 10],\n", " [ 1, 6, 11],\n", " [ 2, 7, 12],\n", " [ 3, 8, 13],\n", " [ 4, 9, 14]])" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "arr.T" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercício 6" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Considere os 3 arrays abaixo\n", "# Retorne o valor do array xarr se o valor for True no array cond. Caso contrário, retorne o valor do array yarr.\n", "xarr = np.array([1.1, 1.2, 1.3, 1.4, 1.5])\n", "yarr = np.array([2.1, 2.2, 2.3, 2.4, 2.5])\n", "cond = np.array([True, False, True, True, False])" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1.1 2.1 True\n", "1.2 2.2 False\n", "1.3 2.3 True\n", "1.4 2.4 True\n", "1.5 2.5 False\n" ] } ], "source": [ "for x, y, c in zip(xarr, yarr, cond):\n", " print(x, y, c)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[1.1, 2.2, 1.3, 1.4, 2.5]" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "resultado = [(x if c else y) for x, y, c in zip(xarr, yarr, cond)]\n", "resultado" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercício 7" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[0 1 2 3 4 5 6 7 8 9]\n" ] } ], "source": [ "# Crie um array A com 10 elementos e salve o array em disco com a extensão npy\n", "# Depois carregue o array do disco no array B\n", "A = np.arange(10)\n", "print(A)\n", "np.save('array_a', A)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[0 1 2 3 4 5 6 7 8 9]\n" ] } ], "source": [ "B = np.load('array_a.npy')\n", "print(B)" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "### Exercício 8" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Considerando a série abaixo, imprima os valores únicos na série\n", "import pandas as pd\n", "obj = pd.Series(['c', 'a', 'd', 'a', 'a', 'b', 'b', 'c', 'c', 'a', 'b'])" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['c', 'a', 'd', 'b'], dtype=object)" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "uniques = obj.unique()\n", "uniques" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "### Exercício 9" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Considerando o trecho de código que conecta em uma url na internet, imprima o dataframe conforme abaixo.\n", "import requests\n", "url = 'https://api.github.com/repos/pandas-dev/pandas/issues'\n", "resp = requests.get(url)\n", "resp" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Slicing columns with mixed types , fails with ValueError'" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data = resp.json()\n", "data[0]['title']" ] }, { "cell_type": "code", "execution_count": 20, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
numbertitlelabelsstate
020975Slicing columns with mixed types <str>,<int> f...[]open
120974BUG: Fix drop_duplicates failure when DataFram...[{'id': 76811, 'url': 'https://api.github.com/...open
220970performance when \"combining\" categories[{'id': 78527356, 'url': 'https://api.github.c...open
320969Getting a ... in my CSV when using to_csv()[]open
420968Sharey keyword for boxplot[]open
520967Column can be extended beyond DataFrame's length[]open
620966BUG: Fix wrong khash method definition[{'id': 76811, 'url': 'https://api.github.com/...open
720965BUG: Fix combine_first converts other columns ...[{'id': 76811, 'url': 'https://api.github.com/...open
820964BUG: Index with integer data and datetime64[ns...[]open
920962df.rank() has different behavior for python2 a...[]open
1020960DOC: add reshaping visuals to the docs (Reshap...[{'id': 134699, 'url': 'https://api.github.com...open
1120958Using apply on a grouper works only if done af...[{'id': 76811, 'url': 'https://api.github.com/...open
1220956ENH: Return DatetimeIndex or TimedeltaIndex bi...[{'id': 49597148, 'url': 'https://api.github.c...open
1320955Building documentation fails with `ImportError...[]open
1420954Correlation inconsistencies between Series and...[]open
1520951Addressing multiindex raises TypeError if indi...[]open
1620948Indexing DataFrame with DateOffset is nearly i...[]open
1720947Allow drop bins when using the cut function[{'id': 76812, 'url': 'https://api.github.com/...open
1820945Data is mismatched with labels after stack wit...[]open
1920944Drop rows based on condition[]open
2020943pd.read_sql does not handle queries that retur...[]open
2120940unclear error with read_sas[]open
2220937BUG: Series(DTI/TDI) loses the frequency infor...[]open
2320936__new__() missing 1 required positional argume...[]open
2420932API: expose `axis` keyword in pandas.core.algo...[{'id': 35818298, 'url': 'https://api.github.c...open
2520930DOC: Index.get_loc Cannot Accept List-like Tol...[]open
2620928Added script to fetch wheels [ci skip][{'id': 131473665, 'url': 'https://api.github....open
2720927read_sas OverflowError: int too big to convert...[]open
2820926BLD: Lint for invalid files in wheels / packages[{'id': 129350, 'url': 'https://api.github.com...open
2920925Series.reset_index(level_name, drop=True) acce...[{'id': 42670965, 'url': 'https://api.github.c...open
\n", "
" ], "text/plain": [ " number title \\\n", "0 20975 Slicing columns with mixed types , f... \n", "1 20974 BUG: Fix drop_duplicates failure when DataFram... \n", "2 20970 performance when \"combining\" categories \n", "3 20969 Getting a ... in my CSV when using to_csv() \n", "4 20968 Sharey keyword for boxplot \n", "5 20967 Column can be extended beyond DataFrame's length \n", "6 20966 BUG: Fix wrong khash method definition \n", "7 20965 BUG: Fix combine_first converts other columns ... \n", "8 20964 BUG: Index with integer data and datetime64[ns... \n", "9 20962 df.rank() has different behavior for python2 a... \n", "10 20960 DOC: add reshaping visuals to the docs (Reshap... \n", "11 20958 Using apply on a grouper works only if done af... \n", "12 20956 ENH: Return DatetimeIndex or TimedeltaIndex bi... \n", "13 20955 Building documentation fails with `ImportError... \n", "14 20954 Correlation inconsistencies between Series and... \n", "15 20951 Addressing multiindex raises TypeError if indi... \n", "16 20948 Indexing DataFrame with DateOffset is nearly i... \n", "17 20947 Allow drop bins when using the cut function \n", "18 20945 Data is mismatched with labels after stack wit... \n", "19 20944 Drop rows based on condition \n", "20 20943 pd.read_sql does not handle queries that retur... \n", "21 20940 unclear error with read_sas \n", "22 20937 BUG: Series(DTI/TDI) loses the frequency infor... \n", "23 20936 __new__() missing 1 required positional argume... \n", "24 20932 API: expose `axis` keyword in pandas.core.algo... \n", "25 20930 DOC: Index.get_loc Cannot Accept List-like Tol... \n", "26 20928 Added script to fetch wheels [ci skip] \n", "27 20927 read_sas OverflowError: int too big to convert... \n", "28 20926 BLD: Lint for invalid files in wheels / packages \n", "29 20925 Series.reset_index(level_name, drop=True) acce... \n", "\n", " labels state \n", "0 [] open \n", "1 [{'id': 76811, 'url': 'https://api.github.com/... open \n", "2 [{'id': 78527356, 'url': 'https://api.github.c... open \n", "3 [] open \n", "4 [] open \n", "5 [] open \n", "6 [{'id': 76811, 'url': 'https://api.github.com/... open \n", "7 [{'id': 76811, 'url': 'https://api.github.com/... open \n", "8 [] open \n", "9 [] open \n", "10 [{'id': 134699, 'url': 'https://api.github.com... open \n", "11 [{'id': 76811, 'url': 'https://api.github.com/... open \n", "12 [{'id': 49597148, 'url': 'https://api.github.c... open \n", "13 [] open \n", "14 [] open \n", "15 [] open \n", "16 [] open \n", "17 [{'id': 76812, 'url': 'https://api.github.com/... open \n", "18 [] open \n", "19 [] open \n", "20 [] open \n", "21 [] open \n", "22 [] open \n", "23 [] open \n", "24 [{'id': 35818298, 'url': 'https://api.github.c... open \n", "25 [] open \n", "26 [{'id': 131473665, 'url': 'https://api.github.... open \n", "27 [] open \n", "28 [{'id': 129350, 'url': 'https://api.github.com... open \n", "29 [{'id': 42670965, 'url': 'https://api.github.c... open " ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "issues = pd.DataFrame(data, columns=['number', 'title', 'labels', 'state'])\n", "issues" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercício 10" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# Crie um banco de dados no SQLite, crie uma tabela, insira registros, \n", "# consulte a tabela e retorne os dados em dataframe do Pandas\n", "import sqlite3\n", "import pandas as pd\n", "query = \"\"\"\n", "CREATE TABLE TESTE\n", "(Cidade VARCHAR(20), \n", " Estado VARCHAR(20),\n", " taxa REAL, \n", " Impostos INTEGER\n", ");\"\"\"\n", "con = sqlite3.connect('dsa.db')\n", "con.execute(query)\n", "con.commit()" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "collapsed": true }, "outputs": [], "source": [ "data = [('Natal', 'Rio Grande do Norte', 1.25, 6),\n", " ('Recife', 'Pernambuco', 2.6, 3),\n", " ('Londrina', 'Paraná', 1.7, 5)]\n", "stmt = \"INSERT INTO TESTE VALUES(?, ?, ?, ?)\"\n", "con.executemany(stmt, data)\n", "con.commit()" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[('Natal', 'Rio Grande do Norte', 1.25, 6),\n", " ('Recife', 'Pernambuco', 2.6, 3),\n", " ('Londrina', 'Paraná', 1.7, 5)]" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cursor = con.execute('select * from teste')\n", "rows = cursor.fetchall()\n", "rows" ] }, { "cell_type": "code", "execution_count": 24, "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", "
CidadeEstadotaxaImpostos
0NatalRio Grande do Norte1.256
1RecifePernambuco2.603
2LondrinaParaná1.705
\n", "
" ], "text/plain": [ " Cidade Estado taxa Impostos\n", "0 Natal Rio Grande do Norte 1.25 6\n", "1 Recife Pernambuco 2.60 3\n", "2 Londrina Paraná 1.70 5" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cursor.description\n", "pd.DataFrame(rows, columns=[x[0] for x in cursor.description])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Fim" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Obrigado - Data Science Academy - facebook.com/dsacademybr" ] } ], "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": "3.6.5" } }, "nbformat": 4, "nbformat_minor": 1 }