# -*- coding: utf-8 -*-
"""
Created on Mon Jan 24 16:48:32 2022

@author: zxy
"""

# 導入包
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
import seaborn as sns; plt.style.use('ggplot')

import sklearn
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.utils import shuffle
from sklearn.metrics import confusion_matrix
from sklearn.manifold import TSNE

# 導入并查看數據
crecreditcard_data=pd.read_csv('./creditcard.csv')
crecreditcard_data.shape,crecreditcard_data.info()

crecreditcard_data.describe()


crecreditcard_data.head()

# 看看欺詐與非欺詐的比例如何
count_classes=pd.value_counts(crecreditcard_data['Class'],sort=True).sort_index()

# 統計下具體數據
count_classes.value_counts()
# 也可以用count_classes[0],count_classes[1]看分別數據

count_classes.plot(kind='bar')
plt.show()

import pandas as pd
import numpy as np
 
# 讀取整個csv文件
csv_data = pd.read_csv("./stock_day.csv")
 
# 讀取指定列索引字段的數據
csv_data = pd.read_csv("./stock_day.csv", usecols=['open', 'close'])
 
# 將我們修改完的csv的文件保存到新的路徑下
csv_data.to_csv('demo.csv')

# 查看新保存的文件
new_data = read_csv('./demo.csv')

csv_data.to_csv('demo.csv', header=True, index=False)

# 生成一個時間的序列，略過周末非交易日
date = pd.date_range('2018-02-27', periods=new_data.shape[1], freq='B')
 
# index代表行索引，columns代表列索引
new_data = pd.DataFrame(new_data, index=date)