我正在做一个小型的机器学习项目。我在一个数据框中收集了该公司在S＆P500中的所有股票行情及其每日价值。问题是当我调用函数

do_ml('BAC')

我收到此错误：

Traceback (most recent call last):
  File "c:\Users\giuli\Desktop\UDEMY COURSES\finance\Git_rep\processing _for_ml.py",line 87,in <module>
    do_ml('BAC')
  File "c:\Users\giuli\Desktop\UDEMY COURSES\finance\Git_rep\processing _for_ml.py",line 72,in do_ml
    X,y,df = extract_featuresets(ticker)
  File "c:\Users\giuli\Desktop\UDEMY COURSES\finance\Git_rep\processing _for_ml.py",line 46,in extract_featuresets
    df['{}_d1'.format(ticker)],File "C:\Python37\lib\site-packages\pandas\core\frame.py",line 2980,in __getitem__
    indexer = self.columns.get_loc(key)
  File "C:\Python37\lib\site-packages\pandas\core\indexes\base.py",line 2899,in get_loc
    return self._engine.get_loc(self._maybe_cast_indexer(key))
  File "pandas\_libs\index.pyx",line 107,in pandas._libs.index.IndexEngine.get_loc
  File "pandas\_libs\index.pyx",line 126,line 152,in pandas._libs.index.IndexEngine._get_loc_duplicates
  File "pandas\_libs\index.pyx",line 169,in pandas._libs.index.IndexEngine._maybe_get_bool_indexer
KeyError: 'BAC_d1'

Thiese是与该函数有关的所有函数：

def remove_extra_characters(df):
    df.rename(columns={old:old.strip() for old in df.columns},inplace=True)


def process_data_for_labels(ticker):
    hm_days=7
    df = pd.read_csv('sp500_joined_closes.csv',index_col = 0 )

    tickers = df.columns.values.tolist()
    df.fillna(0,inplace=True)
    remove_extra_characters(df)

    for i in range(1,hm_days+1):
        df['{}_{}d'.format(ticker,i)] = (df[ticker].shift(-i) - df[ticker]) / df[ticker]

    print(df)

    df.fillna(0,inplace=True)

    return tickers,df



def buy_sell_hold(*args):
    cols = [c for c in args]
    requirements = 0.02
    for col in cols:
        if col > requirements:
            return 1
        if col < requirements:
            return -1
    return 0

def extract_featuresets(ticker):
    tickers,df = process_data_for_labels(ticker)

    df['{}_target'.format(ticker)] = list(map( buy_sell_hold,df['{}_d1'.format(ticker)],df['{}_d2'.format(ticker)],df['{}_d3'.format(ticker)],df['{}_d4'.format(ticker)],df['{}_d5'.format(ticker)],df['{}_d6'.format(ticker)],df['{}_d7'.format(ticker)]))

    vals = df['{}target'.format(ticker)].values.tolist()
    str_vals= [str(i) for i in vals]
    print('Data spread:',Counter(str_vals))
    df.fillna(0,inplace=True)

    df = df.replace([np.inf,-np.inf],np.nan)
    df.dropna(inplace=True)

    df_vals = df[[ticker for ticker in tickers]].pct_change()
    df_vals = df_vals.replace([np.inf,0)
    df_vals.fillna(0,inplace=True)

    X = df_vals.values #Percent change data of comanies.
    y = df['{}target'.format(ticker)].values #target

    return X,df

def do_ml(ticker):
    X,df = extract_featuresets(ticker)
    #setting sets for training and testing giving it 25% of the size each.
    X_train,X_test,y_train,y_test = cross_validation.train_test_split(X,test_size = 0.25)
    #selecting classifier
    clf = neighbors.KNeighborsClassifier()
    #fitting data in classifier
    clf.fit(X_train,y_train)

    confidence = clf.score(X_test,y_test)
    predictions = clf.predict(X_test)
    print('Predicted spread:',Counter(predictions))
    return confidence

问题肯定在extract_feature函数中。我在这里所做的基本上是在我的数据框中创建7列，每个列都包含一个值，该值试图预测当日的价格变化（因此，数据框将显示下周每一天的价格变化）