#coding:utf8
import pandas as pd
import numpy as np
from pandas import Series,DataFrame
 
# 如果有id列，则需先删除id列再进行对应操作，最后再补上
# 统计的时候不需要用到id列,删除的时候需要考虑
# delete row
def 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为考虑带标签
	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))
 
# 如果有字符串类型，则报错
# data normalization -1 to 1
# label_col: 不需考虑的类标，可以为字符串或字符串列表
# 数值类型统一到float64
def 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
 
 
# 创建一个带有缺失值的数据框：
df = pd.DataFrame(np.random.randn(5,3), index=list('abcde'), columns=['one','two','three'])
df.ix[1,:-1]=np.nan
df.ix[1:-1,2]=np.nan
df.ix[0,0]=int(1)
df.ix[2,2]='abc'
 
# 查看一下数据内容：
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]))