python - 'numpy.int6 4' object has no attribute ' 时间戳'

Question

我很难解决这个问题，因为我在谷歌上找不到任何人以前遇到过同样的问题。我是个菜鸟，所以请耐心等待!:)))

import pandas as pd
#import quandl



#df=quandl.get('WIKI/GOOGL')

#df.to_csv('google.csv')
#df=pd.read_csv('google.csv')
df = pd.read_csv(r'C:\Users\c900452\Downloads\20160623 Python\google.csv')



df=df[['Adj. Open','Adj. High','Adj. Low','Adj. Close','Adj. Volume']]

# crude volatility
df['HL_PCT'] = (df['Adj. High'] -df['Adj. Low'])/df['Adj. Close']*100.0

#close and open volatility

df['PCT_change'] = (df['Adj. Close'] - df['Adj. Open']) / df['Adj. Open'] * 100.0

#creating a new dataframe
df = df[['Adj. Close', 'HL_PCT', 'PCT_change', 'Adj. Volume']]

import math
import numpy as np
import pandas as pd
from sklearn import preprocessing, cross_validation, svm
from sklearn.linear_model import LinearRegression



forecast_col = 'Adj. Close'
df.fillna(value = -99999, inplace=True)
forecast_out = int(math.ceil(0.01 * len(df)))
print(forecast_out)

df['label'] = df[forecast_col].shift(-forecast_out)


X = np.array(df.drop(['label'],1))
X = preprocessing.scale(X)
X_lately = X[-forecast_out:]
X = X[:-forecast_out]




df.dropna(inplace=True)

y = np.array(df['label'])
y = np.array(df['label'])


X_train, X_test, y_train, y_test = cross_validation.train_test_split(X,y,test_size=0.2)

clf=LinearRegression(n_jobs=-1)
clf.fit(X_train,y_train)
accuracy = clf.score(X_test,y_test)

forecast_set = clf.predict(X_lately)

print(forecast_set, accuracy, forecast_out)



import datetime
import matplotlib.pyplot as plt
from matplotlib import style

style.use('ggplot')

df['Forecast'] = np.nan

last_date = df.iloc[-1].name
last_unix  = last_date.timestamp()
one_day = 86400
next_unix = last_unix+one_day

for i in forecast_set:
    next_date = datetime.datetime.fromtimestamp(next_unix)
    next_unix += one_day
    df.loc[next_date] = [np.nan for _ in range(len(df.columns)-1)]+[i]

print(df.head())

df['Adj. Close'].plot()    
df['Forcast'].plot()
plt.legend(loc=4)
plt.xlabel('Date')
plt.xlabel('Price')
plt.show()

我收到了主题中所述的错误，为什么？

Answer 1

在读取文件时尝试解析日期列:

df = pd.read_csv(r'C:\Users\c900452\Downloads\20160623 Python\google.csv',
                  header=0, 
                  index_col='Date',
                  parse_dates=True)

这对我有用。欲了解更多详细信息，请阅读pandas.read_csv Documentation