Python使用xlrd、pandas包從Excel讀取數據

#coding=utf-8
# pip install xlrd

import xlrd
def read_from_xls(filepath,index_col_list):
    #filepath：讀取文件路徑，例如：filepath = r'D:/Python_workspace/test.xlsx'
　　#index_col_list：讀取列的索引列表，例如第一、二、三、四列為：[1,2,3,4]
    # 設置GBK編碼
    xlrd.Book.encoding = "gbk"
    rb = xlrd.open_workbook(filepath)
    #print(rb)

    sheet = rb.sheet_by_index(0) #表示Excel的第一個Sheet
    nrows = sheet.nrows
    data_tmp_x = []  #例如數據為x,y,z坐標數據
    data_tmp_y = []
    data_tmp_z = []
    for index_col in index_col_list: #依次選擇第index_col列
        for i in range(nrows):
            tt=i+1   #讀取第tt行，除去第一行的列名
            if tt >= nrows:
                break
            else:
                tmp = float(sheet.cell_value(tt,index_col)) #讀取第幾行第幾列的數據內容
                if index_col == 2:
                    data_tmp_x.append(tmp)
                elif index_col == 3:
                    data_tmp_y.append(tmp)
                elif index_col == 4:
                    data_tmp_z.append(tmp)
    data_tmp = np.mat([data_tmp_x,data_tmp_y,data_tmp_z])
    return data_tmp

# 使用pandas讀取excel
# filepath: xlsx文件路徑名
import pandas as pd
data = pd.read_excel(filepath)
province_name = data['province'].values.tolist() # province為列名，結果形成列表
province_people = data['count'].values.tolist()

 -------- pandas讀取excel —— pd.read_excel --------

部分參數說明：

def read_excel(io,
               sheet_name=0,
               header=0,
               names=None,
               index_col=None,
               usecols=None,
               squeeze=False,
               dtype=None,
               engine=None,
               converters=None,
               true_values=None,
               false_values=None,
               skiprows=None,
               nrows=None,
               na_values=None,
               parse_dates=False,
               date_parser=None,
               thousands=None,
               comment=None,
               skipfooter=0,
               convert_float=True,
               **kwds)

io：excel文件路徑

sheet_name：string, int, mixed list of strings/ints, or None, default 0，sheet表名

    * Defaults to 0 -> 1st sheet as a DataFrame
    * 1 -> 2nd sheet as a DataFrame
    * "Sheet1" -> 1st sheet as a DataFrame
    * [0,1,"Sheet5"] -> 1st, 2nd & 5th sheet as a dictionary of DataFrames
    * None -> All sheets as a dictionary of DataFrames

header：指定作為列名的行，默認為0，即取第一行作為列名；若數據不含列名，則設定 header = None

names：可用列表等參數指定列名序列，如果沒有列名，則需要先設置 header=None；如果只有一列，需要設置為列表形式，例如：['第一列']，否則會出現錯誤：TypeError: Index(...) must be called with a collection of some kind

names : array-like, default None
    List of column names to use. If file contains no header row,
    then you should explicitly pass header=None

index_col：以某一列作為行標簽，也就是行索引

skiprows：從頭開始跳過的行數，可以傳列表

skipfooter：省略從末尾開始的行數

na_values：識別NA/NaN數據，並替換為該值

na_values : scalar, str, list-like, or dict, default None
    Additional strings to recognize as NA/NaN. If dict passed, specific
    per-column NA values. By default the following values are interpreted
    as NaN: '""" + fill("', '".join(sorted(_NA_VALUES)), 70, subsequent_indent="    ") + """'.

squeeze：當傳入數據只有一列時，返回序列Series，而不是Dataframe數據

squeeze : boolean, default False
    If the parsed data only contains one column then return a Series

nrows：要解析的行數

nrows : int, default None
    Number of rows to parse

    .. versionadded:: 0.23.0

 

## 歡迎有錯誤進行指正，也可交流改進