python 数据可视化 -- 读取数据

从 CSV 文件中读取数据（CSV）

import sys
import csv  # python 内置该模块 支持各种CSV文件

file_name = r"..\ch02_data\ch02-data.csv"  # r 指明字符串不用转义
data = []

try:
    with open(file_name) as f:  # 打开文件
        reader = csv.reader(f)  # 获取 reader 对象，通过对该对象的遍历获取文件的所有内容，默认分隔符为“,” 可以通过 dialect 指定分隔符
        header = next(reader)  # 读取文件头
        data = [row for row in reader]  # 读取文件内容，并存放到列表中
except csv.Error as e:
    print("Error reading CSV file at line %s: %s" %(reader.line_num, e))
    sys.exit(-1)

if header:
    print(header)
    print("===========================")

for datarow in data:
    print(datarow)

读取 tab 分隔的文件（csv）

也可以通过传统的 split("\t") 来进行分隔

import csv
import sys

filename = r'../ch02_data/ch02-data.tab'
data = []
try:
    with open(filename) as f:
        reader = csv.reader(f, dialect = csv.excel_tab)   # 指定 tab 分隔符
        header = next(reader)
        data = [row for row in reader]  # 将文件内容读入列表
except csv.Error as e:
    print("Error reading CSV file at line %s: %s" % (reader.line_num, e))
    sys.exit(1)

if header:
    print(header)
    print('===================')
for datarow in data:
    print(datarow)

从 Excel 中读取数据

www.python-excel.org 项目提供的软件包可以方便 python 处理 excel 文件。

该项目提供的 package 有：openpyxl  xlsxwriter  xlrd  xlwt  xlutils 

安装方法：以管理员方式打开 cmd --> pip install xlrd

import xlrd  ## 专门读取 excel 的 package
# from pprint import pprint

file = r"..\ch02_data\ch02-xlsxdata.xlsx"
wb = xlrd.open_workbook(filename = file)  # 读取 excel 文件，返回 xlrd.book.Book 类的实例对象
ws = wb.sheet_by_name("Sheet1")  # 根据 sheet name 读取 sheet 中的数据，返回 xlrd.sheet.Sheet 类的实例对象
data_set = []
for r in range(ws.nrows):  # sheet 的行数
    col = []
    for c in range(ws.ncols):  # sheet 的列数
        col.append(ws.cell(r, c).value)  # 获取指定的 Cell 的实例对象，通过  value 属性获取值
    data_set.append(col)
# pprint(data_set)
for i in data_set:
    print(i)

从定宽数据文件导入数据（struct）

import struct  # 该 module 执行 python 值和 C 结构体之间的转换，从而形成 python 字节对象

datafile = r"../ch02_data/ch02-fixed-width-1M.data"
# mask = bytes('9s15s5s', encoding = 'utf-8')  # bytes 内置函数返回一个新的 bytes 对象。
mask = '9s15s5s'
with open(datafile, 'rb') as f:  # 以二进制格式打开一个文件用于只读
    for line in f:
        fields = struct.Struct(mask).unpack_from(line)  # 根据 mask 描述的格式，将 bytes 反向解析出来，返回一个元组
        print('fields: ', [field.strip() for field in fields])

 从数据库读写数据

import sqlite3
import sys
from builtins import str

# 向数据库中写入数据
if len(sys.argv) < 2:
    print("Error: You must supply at least SQL script.")
    print("Usage: %s table.db ./sql-dump.sql" % (sys.argv[0]))
    sys.exit(1)
 
script_path = sys.argv[2]  # sql脚本文件
 
if len(sys.argv)== 3:
    db = sys.argv[1]  # 写入的数据库文件
else:
    db = ":memory:"
 
try:
    con = sqlite3.connect(db)  # 返回一个 sqlite3.Connection 对象实例
    with con:
        cur = con.cursor()  # 返回一个 sqlite3.Cursor 对象实例
        with open(script_path, 'rb') as f:
            cur.executescript(f.read().decode())
except sqlite3.Error as err:
    print("Error occured: %s" % err)

# 从数据库中读取数据
db = sys.argv[1]
try:
    con = sqlite3.connect(db)
    with con:
        cur = con.cursor()  # 得到一个游标对象，用于遍历数据库放回的结果集中的记录
        query = 'SELECT ID, Name, Population FROM City ORDER BY Population DESC LIMIT 10'
        con.text_factory = str  # 该属性控制返回对象的数据类型
        cur.execute(query)  # 执行查询语句
        resultset = cur.fetchall()  # 获取查询结果集汇总所有的记录，返回一个列表，每个查询记录是一个元组
        col_names = [cn[0] for cn in cur.description]  # description 属性提供了列的描述信息，每列的描述是一个7个元素的元组
        print("%10s %30s %10s" % tuple(col_names))
        print("="*(10 + 1+ 30 + 1 + 10))

        for row in resultset:
            print("%10s %30s %10s" % row)
except sqlite3.Error as err:
    print("[ERROR]: ", err)

sql 脚本文件

DROP TABLE IF EXISTS 'City';
CREATE TABLE `City` (
  `ID` int(11) NOT NULL ,
  `Name` char(35) NOT NULL ,
  `CountryCode` char(3) NOT NULL ,
  `District` char(20) NOT NULL ,
  `Population` int(11) NOT NULL ,
  PRIMARY KEY (`ID`)
);

INSERT INTO `City` VALUES (1,'Kabul','AFG','Kabol',1780000);
INSERT INTO `City` VALUES (2,'Qandahar','AFG','Qandahar',237500);
INSERT INTO `City` VALUES (3,'Herat','AFG','Herat',186800);
INSERT INTO `City` VALUES (4,'Mazar-e-Sharif','AFG','Balkh',127800);
INSERT INTO `City` VALUES (5,'Amsterdam','NLD','Noord-Holland',731200);
INSERT INTO `City` VALUES (6,'Rotterdam','NLD','Zuid-Holland',593321);
INSERT INTO `City` VALUES (7,'Haag','NLD','Zuid-Holland',440900);
INSERT INTO `City` VALUES (8,'Utrecht','NLD','Utrecht',234323);
INSERT INTO `City` VALUES (9,'Eindhoven','NLD','Noord-Brabant',201843);
INSERT INTO `City` VALUES (10,'Tilburg','NLD','Noord-Brabant',193238);
INSERT INTO `City` VALUES (11,'Groningen','NLD','Groningen',172701);
INSERT INTO `City` VALUES (12,'Breda','NLD','Noord-Brabant',160398);
INSERT INTO `City` VALUES (13,'Apeldoorn','NLD','Gelderland',153491);
INSERT INTO `City` VALUES (14,'Nijmegen','NLD','Gelderland',152463);
INSERT INTO `City` VALUES (15,'Enschede','NLD','Overijssel',149544);

读取图片

import matplotlib.pyplot as plt
import scipy.misc

bug = scipy.misc.imread('stinkbug.png')


plt.figure(1)
plt.gray()
plt.imshow(bug)
plt.colorbar()

plt.figure(2)
bug = bug[:,:,0]
plt.subplot(121)
plt.imshow(bug)

zbug = bug[100:350, 140:350]
 
plt.subplot(122)
plt.imshow(zbug)
plt.colorbar()
plt.show()