利用Python中的pandas、matplotlib对xlsx和csv文件批量绘图

import matplotlib matplotlib.use('agg') import matplotlib.pyplot as plt import pandas as pd import numpy as np import glob import os import re import datetime as dt import chardet import warnings warnings.filterwarnings('ignore') # 设置字体, 解决中文乱码问题 plt.rcParams['font.sans-serif'] = ['Microsoft YaHei'] # 解决图像中的'-'负号的乱码问题 plt.rcParams['axes.unicode_minus'] = False # 获取当前脚本文件所在目录 path_current = os.getcwd() # 获取当前脚本文件所在目录的上一级目录 path_pardir = os.path.dirname(path_current) print(path_pardir) file_lists_Input = glob.glob(path_pardir + '/Input/*.xlsx') print(file_lists_Input) file_lists_config = glob.glob(path_pardir + '/config/*.csv') print(file_lists_config) file_lists_split = glob.glob(path_pardir + '/split/*.csv') print(file_lists_split) # 自动识别文件编码格式 def get_encoding(file): with open(file, 'rb') as f: tmp = chardet.detect(f.read()) return tmp['encoding'] # 数据格式转换 def data_format_exchange(data_list): for each_data in data_list: # 判断数据是否是字符串格式 if isinstance(each_data, str): # 若数据是字符串格式, 再判断数据是否是带% if re.match(r'[\d.]+%', each_data, re.I): # 若带%, 去掉%后, 再转化成float型 each_data_trans = float(each_data[:-1]) # print('The type of the number {} is {}'.format(each_data_trans, type(each_data_trans))) else: # 若不带%, 直接转化成float型 each_data_trans = float(each_data) # print('The type of the number {} is {}'.format(each_data_trans, type(each_data_trans))) index_num = data_list.index(each_data) data_list[index_num] = each_data_trans # 获取config数据, 并存储在字典中 def get_config_data(file_list_config): for files in file_list_config: dict_config = {} encoding = get_encoding(files) print('$$$encoding:', encoding) pd.options.display.max_columns = None df = pd.read_csv(files, encoding=encoding) # print(df.tail()) # print('#' * 50) dict_config.setdefault('Sort_Gar', {}) dict_config.setdefault('Sort_Ban', {}) dict_config.setdefault('Sort_Para', {}) dict_config.setdefault('Sort_Arg', {}) dict_config.setdefault('Sort_Argc', {}) # print('$$$dict_config:', dict_config) for i in range(len(df['Sort_Gar'])): dict_config['Sort_Gar'].setdefault(df['Sort_Gar'][i], []).append(df['Gar_Item'][i]) for i in range(len(df['Sort_Ban'])): dict_config['Sort_Ban'].setdefault(df['Sort_Ban'][i], []).append(df['Ban_Item'][i]) for i in range(len(df['Sort_Para'])): dict_config['Sort_Para'].setdefault(df['Sort_Para'][i], []).append(df['Para_Item'][i]) for i in range(len(df['Sort_Arg'])): dict_config['Sort_Arg'].setdefault(df['Sort_Arg'][i], []).append(df['Arg_Item'][i]) for i in range(len(df['Sort_Argc'])): dict_config['Sort_Argc'].setdefault(df['Sort_Argc'][i], []).append(df['Argc_Item'][i]) # 获取dict_config的key, 并存储在dict_config_keys中 dict_config_keys = list(dict_config) # print('$$$dict_config_keys:', dict_config_keys) for dict_config_key in dict_config_keys: embedded_keys = list(dict_config[dict_config_key]) for embedded_key in embedded_keys: if str(embedded_key) == 'nan': del dict_config[dict_config_key][embedded_key] # print('###dict_config是:###', dict_config) return dict_config # 获取split数据, 并存储在DataFrame中 def get_split_data(file_list_split): for files in file_list_split: encoding = get_encoding(files) # print(encoding) pd.options.display.max_columns = None df_split = pd.read_csv(files, encoding=encoding) # 删除df_split中全为空的行 df_split = df_split.dropna(axis=0, how='all') # print(df_split.head()) # print('#' * 50) return df_split # 获取Input数据, 并存储起来 def get_Input_data(file_list_Input): for files in file_list_Input: # sheet_name=None可以让read_excel()函数读取该excel中所有的sheet df_input_dict = pd.read_excel(files, sheet_name=None) # print(list(df_input_dict.keys())) # df_Gar = df_input_dict['Gar'] # df_Ban = df_input_dict['Ban'] # df_Para = df_input_dict['Para'] # df_Arg = df_input_dict['Arg'] # df_Argc = df_input_dict['Argc'] # print(df_Gar.head()) # element = df_Gar['Apple_Large_4kg'][0] # print('The type of the element is:', type(element)) # element_trans = df_Gar['Apple_Large_4kg'].astype(float) # print(type(element_trans)) # cols = list(df_Gar) # print('The column label of the df is:', cols) # for i in df_Gar['Apple_Large_4kg']: # i = float(i[:-1]) # print('The type of the number {} is {}'.format(i, type(i))) # data = df_Gar['Apple_Large_4kg'] # data = df_Arg['SB'] # data_format_exchange(data) # print(data) # print('#' * 50) return df_input_dict class BarchartFather: def __init__(self, Barchart_byGroup_xlabels, Barchart_byGroup_data, Barchart_byGroup_legend, title_name, picture_name, number, Barchart_byGroup_ylabels): self.local_path = path_pardir + '/output/' + str(Type_ID) + '_' + Nowtime + '/' self.Barchart_byGroup_xlabels = Barchart_byGroup_xlabels self.Barchart_byGroup_data = Barchart_byGroup_data self.Barchart_byGroup_legend = Barchart_byGroup_legend self.title_name = title_name self.picture_name = picture_name self.number = number self.Barchart_byGroup_ylabels = Barchart_byGroup_ylabels self.fig = plt.figure(figsize=(8, 6), facecolor='#B0C4DE') self.ax = self.fig.add_subplot(facecolor='white') ################################################################################################################ # self.color_list = [深橙色, 纯蓝色, 纯绿色, 洋红色, 青色, 橙红色, 淡蓝色, 紫色, 纯红色, 酸橙色, 棕色, 淡珊瑚色,\ # 靛青色, 橄榄色, 水鸭色, 暗淡的灰色, 热情的粉红色, 兰花的紫色, 黑色, 深粉色, 淡钢蓝色, 橄榄土褐色,\ # 深紫罗兰色, 适中的紫色, 道奇蓝色] ################################################################################################################ self.color_list = ['#FF8C00', '#0000FF', '#008000', '#FF00FF', '#00FFFF', '#FF4500', '#87CEFA', '#800080', '#FF0000', '#00FF00', '#A52A2A', '#F08080', '#4B0082', '#808000', '#008080', '#696969', '#FF69B4', '#DA70D6', '#000000', '#FF1493', '#B0C4DE', '#556B2F', '#9400D3', '#9370DB', '#1E90FF'] self.length = len(self.Barchart_byGroup_xlabels) self.x_locs = np.arange(self.length) self.total_width = 0.8 self.box_total_width = self.total_width * 0.85 self.interval_total_width = self.total_width * 0.15 self.width = self.total_width / self.number self.box_width = self.box_total_width / self.number ################################################### if self.number == 1: self.interval_width = self.interval_total_width else: self.interval_width = self.interval_total_width / (self.number - 1) ########################