KeyError：使用Featu的“轴中不包含标签['Adj Close']”

Question

我不知道这里发生了什么事。你知道吗

我正在用Pandas Datareader下载历史股票数据，经过一些小的操作（例如重新排列dataframe、添加移动平均值等），我将dataframe传递给FeatureTools，以进行快速的自动特征工程，它通过向dataframe添加新列来完成这项工作。。。你知道吗

但是后来我将它传递给FeatureSelector（删除所有高度相关、不重要的列等），但是我收到一个问题，FeatureSelector在数据集中找不到我试图指向的“label”列（Adj Close）。我是FeatureSelector的新手，所以我还不完全确定如何使用它。从那里，它将把数据传递给TPOT进行自动回归。你知道吗

我已经包括我的完整代码在这里，我知道你不应该，但它将是一个工作的代码，任何人都可以尝试和看到我的问题在他们这边。我得到的错误是：

KeyError: "labels ['Adj Close'] not contained in axis"

在删除步骤中，FeatureSelector似乎正在删除“Adj Close”标签/列，但我认为这就是我们将其分配给内部“label=”部分的原因？有什么建议都可以。我很想让它工作。只需输入一个股票代码就可以开始了（例如CLVS）。谢谢！你知道吗

ticker_input = input('Which stock ticker would you like to predict?') # Start with CLVS for testing

print('Getting the historical data for: ',ticker_input)

# Downloading historical data as dataframe
from datetime import datetime
from pandas_datareader import data as web
import pandas as pd
ex = 'yahoo'
start = datetime(2010, 1, 1)
end = datetime.now()
df = web.DataReader(ticker_input, ex, start, end).reset_index()

# Create the prediction dataset
df = df.drop(['Close'],axis=1)
df['PrevHi'] = df['High'].shift(1)
df['PrevLo'] = df['Low'].shift(1)
df['PrevClose'] = df['Adj Close'].shift(1)
df['PrevVol'] = df['Volume'].shift(1)
df['PrevOpen'] = df['Open'].shift(1)
df = df.drop(['High','Low','Volume'],axis=1)
# Get the 9 and 20 MA values
df['9MA'] = df['Open'].rolling(window=9).mean()
df['20MA'] = df['Open'].rolling(window=20).mean()


import time
# Reshape the df
df2 = df[['Date','Open','PrevOpen','PrevHi','PrevLo','PrevClose','PrevVol','9MA','20MA','Adj Close']]
df2.dropna(how='all') # THIS DROP ISN'T DROPPING ROWS W/ BLANK VALUES FOR SOME REASON???



# Auto Feature Engineering using Feature Tools
import featuretools as ft
#print(ft.list_primitives().to_string()) # To get full list of primitives that could be used
print('Adding the engineered features to the dataframe. This may take a while...')
es = ft.EntitySet(id = 'stockdata')
es.entity_from_dataframe(entity_id = 'data', dataframe = df2, 
                         make_index = False,index = 'Date')
# Run deep feature synthesis with transformation primitives
feature_matrix, feature_defs = ft.dfs(entityset = es, target_entity = 'data', max_depth=2,verbose=True,

                    agg_primitives = ['skew','mean','median',
                    'all','count','num_unique','trend','max','mode',
                    'std','sum','min'],
                    trans_primitives = ['divide_numeric'])
                    # 'diff',
                    # 'greater_than',
                    # 'less_than_equal_to',
                    # 'cum_mean',
                    # 'time_since',
                    # 'cum_sum',
                    # 'add_numeric',
                    # 'multiply_numeric',
                    # 'greater_than_equal_to',
                    # 'negate',
                    # 'cum_min',
                    # 'subtract_numeric',
                    # 'not',
                    # 'cum_count',
                    # 'modulo_numeric',
                    # 'less_than'])
print(feature_matrix.head())
df2 = feature_matrix
df2.to_csv('FeatureMatrix.csv')

# Trying to now name all the feature columns and label for FeatureSelector...
features = df2.drop(['Adj Close'],axis=1)
label = df2['Adj Close'].values
# Now, drop all columns of low importance
from feature_selector import FeatureSelector
fs = FeatureSelector(data = features, labels = label)
fs.identify_all(selection_params = {'missing_threshold': 0.6,    
                                    'correlation_threshold': 0.98, 
                                    'task': 'regression',    
                                    'eval_metric': 'mse', 
                                    'cumulative_importance': 0.99})
df2 = fs.remove(methods = 'all')
# Somewhere above it's not recognizing my Adj Close label anymore?
# Training dataset
df = df2.iloc[:-90] # subtracting 90 rows/days to use as the predictions dataset later
print('Printing training dataframe...')
print(df)
# Prediction dataset for later use
prediction_df = df2.iloc[-90:]
print('Printing prediction dataframe for later use...')
print(prediction_df)
# Can keep adding to the dataset with things like PrevIndustryHi,Lo,Close,Open and other metrics
print('Pausing for 20 seconds to review before training...')
time.sleep(20)




# Now, train a TPOT Regressor
from tpot import TPOTRegressor
from sklearn.model_selection import train_test_split
import os
features = df.drop(['Adj Close'],axis=1)
label = df['Adj Close']
X_train, X_test, y_train, y_test = train_test_split(features, label,
                                                    train_size=0.75, test_size=0.25)
# Create a folder to cache the pipeline work (use if not using auto)
# if os.path.exists('./PipelineCache'):
#     pass
# else:
#     os.mkdir('./PipelineCache')
tpot = TPOTRegressor(generations=10, population_size=40, verbosity=2) #memory='./PipelineCache',       memory='auto',
tpot.fit(X_train, y_train)
predictions = (tpot.predict(X_test))
actuals = y_test
last_row = df.tail(1)
print('The last closing price was :')
print(last_row['Adj Close'])
print("TPOT's final score on training data is : ")
print(tpot.score(X_test, y_test))
if os.path.exists('./Exported Pipelines'):
    pass
else:
    os.mkdir('./Exported Pipelines')
tpot.export('./Exported Pipelines/1day-prediction-pipeline.py')


# Now, use the TPOT model to predict on the held out predictions dataset
from sklearn.metrics import mean_squared_error
features = prediction_df.drop(['Adj Close'], axis=1)
labels = prediction_df['Adj Close']
# Fit the model to the prediction_df and predict the labels
#tpot.fit(features, labels)
results = tpot.predict(features)
predictions_list = []
for preds in results:
    predictions_list.append(preds)
prediction_df['Predictions'] = predictions_list
prediction_df.to_csv('PredictionsPerformance.csv', index=True)
print('The Mean Square Error of the predictions is :')
print(mean_squared_error(labels,results))
print('DONE!')

# Clear the cache directory when you don't need it anymore.
# If you're testing the same dataset over and over, use the
# same cache file
#from shutil import rmtree
#rmtree('./PipelineCache')

Answer 1

作为一种解决方法，我只是在删除过程之后重新添加了df列，其中包含adj close，如下所示：

# Trying to now name all the feature columns and label for FeatureSelector...
features = df.drop("Adj Close", axis=1)
label = df["Adj Close"]
# Now, drop all columns of low importance
from feature_selector import FeatureSelector
fs = FeatureSelector(data = features, labels = label)
fs.identify_all(selection_params = {'missing_threshold': 0.6,    
                                    'correlation_threshold': 0.98, 
                                    'task': 'regression',    
                                    'eval_metric': 'mse', 
                                    'cumulative_importance': 0.99})
all_to_remove = fs.check_removal()
print(all_to_remove[:])
df = fs.remove(methods = 'all')

# Re-Add the Adj Close to the df because FeatureTools removes it once you assign it as the label for some reason
df['Adj Close'] = label