First of all, hello everyone. I am halfway though Python Programming for Finance - Creating targets for machine learning labels, and I have a csv with some historical stock data that I'm reading into pandas:
def process_data_for_labels(ticker):
hm_days = 7
df = pd.read_csv('file.csv', index_col=0)
tickers = df.columns.values.tolist()
df.fillna(0, inplace=True)
for i in range(1, hm_days + 1):
df['{}_{}d'.format(ticker, i)] = (df[ticker].shift(-i) - df[ticker]) / df[ticker]
df.fillna(0, inplace=True)
return tickers, df
def buy_sell_hold(*args):
cols = [c for c in args]
requirement = 0.02
for col in cols:
if col > requirement:
# Buy = 1 , Sell = 1 , Hold = 0
return 1
if col < -requirement:
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['{}_1d'.format(ticker)],
df['{}_2d'.format(ticker)],
df['{}_3d'.format(ticker)],
df['{}_4d'.format(ticker)],
df['{}_5d'.format(ticker)],
df['{}_6d'.format(ticker)],
df['{}_7d'.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, -np.inf], 0)
df_vals.fillna(0, inplace=True)
X = df_vals.values
y = df['{}_target'.format(ticker)].values
return X, y, df
extract_featuresets('XOM')
However, when I run it , I get the following error :
File "pandas\_libs\index.pyx", line 132, in pandas._libs.index.IndexEngine.get_loc (pandas\_libs\index.c:5280)
File "pandas\_libs\index.pyx", line 154, in pandas._libs.index.IndexEngine.get_loc (pandas\_libs\index.c:5126)
File "pandas\_libs\hashtable_class_helper.pxi", line 1210, in pandas._libs.hashtable.PyObjectHashTable.get_item (pandas\_libs\hashtable.c:20523)
File "pandas\_libs\hashtable_class_helper.pxi", line 1218, in pandas._libs.hashtable.PyObjectHashTable.get_item (pandas\_libs\hashtable.c:20477)
KeyError: 'ZTS_target'
By the looks of the error, I think it was complaining about the ZTS column data, tried formatting it in a different manner, and when everything else failed, I tried removing it, and then the error went to the Company column data right before it.
If you run the function with extract_featuresets('ZTS'), it wont fail, but with all the other tickers do.
Any ideas how to fix it? Thanks!
