Python 加载、读取CSV文件

import os import sys import pandas as pd import numpy as np import matplotlib.pyplot as plt def Load_CSV_dataset(csv_file): print(csv_file) data = pd.read_csv(csv_file) #print(data) Id = pd.DataFrame(data, columns=['id']) X = pd.DataFrame(data, columns=['x']) Y = pd.DataFrame(data, columns=['y']) G = pd.DataFrame(data, columns=['g']) nseq = Id.to_numpy() nx = X.to_numpy() ny = Y.to_numpy() ng = G.to_numpy() seq = nseq.reshape(np.size(nseq)) x = nx.reshape(np.size(nx)) y = ny.reshape(np.size(ny)) g = ng.reshape(np.size(ng)) return seq,x,y,g def Load_CSV_File(csv_file): data = pd.read_csv(csv_file) X = pd.DataFrame(data, columns=['dmaxz','davgz','dtheta','dmg','sstdev','cstddev']) Y = pd.DataFrame(data, columns=['result']).replace({True: 1, False: 0}) # map True/False to Classes: 0,1,2,... target_count = Y.value_counts() x = X.to_numpy() yn = Y.to_numpy() y = yn.reshape(np.size(yn)) return x,y def Load_CSV_Folder(csv_dir): ext = "*.csv" all_csv_files = [file for path, subdir, files in os.walk(csv_dir) for file in glob(os.path.join(path, ext))] #print(all_csv_files) X = np.empty((0, 6), float) Y = np.array([]) for csv in all_csv_files: x,y = Load_CSV_File(csv) X = np.vstack((X, x)) Y = np.append(Y, y) return X,Y def Load_CSV_Dataset(path): if os.path.isfile(path): return Load_CSV_File(path) if os.path.isdir(path): return Load_CSV_Folder(path) print('Err: can not load csv file') sys.exit() return [],[] if __name__ == "__main__": if len(sys.argv)<2: print("Usage(parse csv file):\n ") sys.exit() #print(sys.argv[1:], type(sys.argv[1:])) sys.exit(Run_Curve_Fitting(sys.argv[1:]))