#coding:utf8import pandas as pdimport numpy as npfrom pandas import Series,DataFrame # 如果有id列，則需先刪除id列再進行對應操作，最后再補上# 統計的時候不需要用到id列,刪除的時候需要考慮# delete rowdef row_del(df, num_percent, label_len = 0):	#print list(df.count(axis=1))	col_num = len(list(list(df.values)[1])) - label_len # -1為考慮帶標簽	if col_num<0:		print 'Error'	#print int(col_num*num_percent)	return df.dropna(axis=0, how='any', thresh=int(col_num*num_percent)) # 如果有字符串類型，則報錯# data normalization -1 to 1# label_col: 不需考慮的類標，可以為字符串或字符串列表# 數值類型統一到float64def data_normalization(df, label_col = []):	lab_len = len(label_col)	print label_col	if lab_len>0:		df_temp = df.drop(label_col, axis = 1)		df_lab = df[label_col]		print df_lab	else:		df_temp = df	max_val = list(df_temp.max(axis=0))	min_val = list(df_temp.min(axis=0))	mean_val = list((df_temp.max(axis=0) + df_temp.min(axis=0)) / 2)	nan_values = df_temp.isnull().values	row_num = len(list(df_temp.values))	col_num = len(list(df_temp.values)[1])	for rn in range(row_num):		#data_values_r = list(data_values[rn])		nan_values_r = list(nan_values[rn])		for cn in range(col_num):			if nan_values_r[cn] == False:				df_temp.values[rn][cn] = 2 * (df_temp.values[rn][cn] - mean_val[cn])/(max_val[cn] - min_val[cn])			else:				print 'Wrong'	for index,lab in enumerate(label_col):		df_temp.insert(index, lab, df_lab[lab])	return df_temp  # 創建一個帶有缺失值的數據框：df = pd.DataFrame(np.random.randn(5,3), index=list('abcde'), columns=['one','two','three'])df.ix[1,:-1]=np.nandf.ix[1:-1,2]=np.nandf.ix[0,0]=int(1)df.ix[2,2]='abc' # 查看一下數據內容：print '/ndf1'print df print row_del(df, 0.8) print '-------------------------' df = data_normalization(df, ['two', 'three'])print df print df.dtypes print (type(df.ix[2,2]))