Convert get_financial_stmts data to pandas DataFrame

[chinobing]

Sample Code

from yahoofinancials import YahooFinancials
import pandas as pd

def dropnested(alist):
    outputdict = {}
    dates = []
    for dic in alist:
        for key, value in dic.items():
            dates.append(key.replace('-',''))
            if isinstance(value, dict):
                for k2, v2, in value.items():
                    outputdict[k2] = outputdict.get(k2, []) + [v2]
            else:
                outputdict[key] = outputdict.get(key, []) + [value]

    return outputdict, dates    

tickers = ['601012.SS','002129.SZ']
yahoo_financials = YahooFinancials(tickers)
income = yahoo_financials.get_financial_stmts('annual', 'income', reformat=True)
data = income['incomeStatementHistory']

df =  pd.DataFrame()
for ticker in tickers:
    t_data = data[ticker]
    outputdict, dates = dropnested(t_data)
    _df = pd.DataFrame.from_dict(outputdict).apply(pd.to_numeric)
    _df['code'] = ticker
    end_date = pd.Series(dates, name='end_date')
    norm_df = pd.concat([_df, end_date], axis=1)
    norm_df = norm_df.set_index('end_date')
    df = df.append(norm_df)

output

Credits:

• ycx - stackoverflow

[AwesomeCap]

---

ValueError Traceback (most recent call last) /var/folders/5z/nfxgl_ps6qlf5tvrct964q980000gn/T/ipykernel_25037/2953129566.py in 12 t_data = data[ticker] 13 outputdict, dates = dropnested(t_data) ---> 14 _df = pd.DataFrame.from_dict(outputdict).apply(pd.to_numeric) 15 _df['code'] = ticker 16 end_date = pd.Series(dates, name='end_date')

~/Library/Python/3.7/lib/python/site-packages/pandas/core/frame.py in from_dict(cls, data, orient, dtype, columns) 1307 raise ValueError("only recognize index or columns for orient") 1308 -> 1309 return cls(data, index=index, columns=columns, dtype=dtype) 1310 1311 def to_numpy(

~/Library/Python/3.7/lib/python/site-packages/pandas/core/frame.py in init(self, data, index, columns, dtype, copy) 466 467 elif isinstance(data, dict): --> 468 mgr = init_dict(data, index, columns, dtype=dtype) 469 elif isinstance(data, ma.MaskedArray): 470 import numpy.ma.mrecords as mrecords

~/Library/Python/3.7/lib/python/site-packages/pandas/core/internals/construction.py in init_dict(data, index, columns, dtype) 281 arr if not is_datetime64tz_dtype(arr) else arr.copy() for arr in arrays 282 ] --> 283 return arrays_to_mgr(arrays, data_names, index, columns, dtype=dtype) 284 285

~/Library/Python/3.7/lib/python/site-packages/pandas/core/internals/construction.py in arrays_to_mgr(arrays, arr_names, index, columns, dtype, verify_integrity) 76 # figure out the index, if necessary 77 if index is None: ---> 78 index = extract_index(arrays) 79 else: 80 index = ensure_index(index)

~/Library/Python/3.7/lib/python/site-packages/pandas/core/internals/construction.py in extract_index(data) 395 lengths = list(set(raw_lengths)) 396 if len(lengths) > 1: --> 397 raise ValueError("arrays must all be same length") 398 399 if have_dicts:

ValueError: arrays must all be same length

[roadfoodr]

@AwesomeCap in the third code block, modify the 5th code line as:

_df = pd.DataFrame.from_dict(outputdict, orient='index').T.apply(pd.to_numeric)

See https://stackoverflow.com/a/40442094