In [0]:
import pandas as pd
from fbprophet import Prophet 
import warnings
warnings.filterwarnings("ignore", category=RuntimeWarning) 

df = pd.read_csv('https://raw.githubusercontent.com/danielcaraway/data/master/Zip_Zhvi_SingleFamilyResidence.csv', encoding='latin')
In [5]:
to_drop = "1996-04	1996-05	1996-06	1996-07	1996-08	1996-09	1996-10	1996-11	1996-12".split()
df_97 = df.drop(to_drop, axis=1)
df_97_nona = df_97.dropna(subset=['1997-01'])
len(df_97_nona)
Out[5]:
13916
In [0]:
df = df_97_nona.copy()
columns = df.columns[:7].values
region_reference = pd.DataFrame(data=df, columns=columns)
to_drop = ['RegionID',
 'City',
 'State',
 'Metro',
 'CountyName',
 'SizeRank']
just_numbers = df.drop(to_drop, axis=1)
df_t = just_numbers.set_index('RegionName').T
df_t.reset_index(inplace=True)
df_t['year'] = df_t.apply(lambda x: x['index'].split('-')[0], axis=1)
by_year = pd.DataFrame(df_t.groupby('year').mean())
by_year_t = by_year.reset_index()
by_year_t['year'] = by_year_t['year'].astype('datetime64[ns]') 
by_year_t.set_index('year', inplace=True)
by_year_t2 = by_year_t.T
by_year_t2.reset_index(inplace=True)
In [0]:
df = by_year_t2.copy()
df_sm = df[:5]
zip_table = []
def get_prophet_predictions(row):
  mini = pd.DataFrame(row)
  mini['ds'] = row.index
  mini['y'] = row.values
  df = mini.iloc[1:]

  m = Prophet()
  m.fit(df)
  invest_price = df.tail(1)
  future = m.make_future_dataframe(periods=60, freq='M')
  fcst = m.predict(future)
  sell_price = fcst.tail(1)

  roi = sell_price['trend'].values[0] - invest_price['y'].values[0]
  return pd.Series((fcst, roi))
In [10]:
df_sm[['forecast','roi']] = df_sm.apply(lambda x: get_prophet_predictions(x), axis=1)
# df[['forecast','roi']] = df.apply(lambda x: get_prophet_predictions(x), axis=1)

INFO:fbprophet:Disabling weekly seasonality. Run prophet with weekly_seasonality=True to override this.
INFO:fbprophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.
INFO:fbprophet:n_changepoints greater than number of observations.Using 17.
INFO:fbprophet:Disabling weekly seasonality. Run prophet with weekly_seasonality=True to override this.
INFO:fbprophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.
INFO:fbprophet:n_changepoints greater than number of observations.Using 17.
INFO:fbprophet:Disabling weekly seasonality. Run prophet with weekly_seasonality=True to override this.
INFO:fbprophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.
INFO:fbprophet:n_changepoints greater than number of observations.Using 17.
INFO:fbprophet:Disabling weekly seasonality. Run prophet with weekly_seasonality=True to override this.
INFO:fbprophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.
INFO:fbprophet:n_changepoints greater than number of observations.Using 17.
INFO:fbprophet:Disabling weekly seasonality. Run prophet with weekly_seasonality=True to override this.
INFO:fbprophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.
INFO:fbprophet:n_changepoints greater than number of observations.Using 17.
INFO:fbprophet:Disabling weekly seasonality. Run prophet with weekly_seasonality=True to override this.
INFO:fbprophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.
INFO:fbprophet:n_changepoints greater than number of observations.Using 17.
/usr/local/lib/python3.6/dist-packages/pandas/core/frame.py:3509: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
In [11]:
# df.to_csv('prophet_df.csv')
Out[11]:
year RegionName 1997-01-01 00:00:00 1998-01-01 00:00:00 1999-01-01 00:00:00 2000-01-01 00:00:00 2001-01-01 00:00:00 2002-01-01 00:00:00 2003-01-01 00:00:00 2004-01-01 00:00:00 2005-01-01 00:00:00 2006-01-01 00:00:00 2007-01-01 00:00:00 2008-01-01 00:00:00 2009-01-01 00:00:00 2010-01-01 00:00:00 2011-01-01 00:00:00 2012-01-01 00:00:00 2013-01-01 00:00:00 2014-01-01 00:00:00 2015-01-01 00:00:00 2016-01-01 00:00:00 2017-01-01 00:00:00 2018-01-01 00:00:00 2019-01-01 00:00:00 forecast roi
0 60657 378192.833333 389723.833333 453431.500000 521798.916667 586183.833333 628344.916667 6.691198e+05 7.073292e+05 7.562488e+05 8.070008e+05 8.102088e+05 8.231563e+05 7.720613e+05 746086.833333 709742.416667 710565.666667 791568.166667 8.466048e+05 8.935743e+05 9.266148e+05 9.397620e+05 9.536783e+05 9.566285e+05 ds trend ... multiplicat... -243313.774765
1 77494 209368.250000 206195.250000 212468.750000 223155.583333 226383.916667 226765.000000 2.311428e+05 2.401042e+05 2.466654e+05 2.498909e+05 2.580278e+05 2.607339e+05 2.610133e+05 267443.583333 260171.666667 264811.166667 283496.833333 3.155041e+05 3.351682e+05 3.324876e+05 3.300152e+05 3.334704e+05 3.347144e+05 ds trend ... multiplicat... -158187.740715
2 60614 573575.666667 616168.166667 706178.750000 804170.666667 905689.416667 983081.333333 1.042087e+06 1.086231e+06 1.164892e+06 1.234957e+06 1.246696e+06 1.179971e+06 1.070229e+06 984387.583333 909385.583333 868096.583333 959294.333333 1.032766e+06 1.095943e+06 1.142199e+06 1.175260e+06 1.194322e+06 1.190550e+06 ds trend ... multiplicat... -722240.584607
3 77449 97162.916667 99462.916667 102394.750000 105518.250000 106366.250000 109551.000000 1.137417e+05 1.198598e+05 1.240328e+05 1.242390e+05 1.289552e+05 1.259122e+05 1.204772e+05 120319.166667 112696.750000 111168.416667 123927.750000 1.402042e+05 1.548712e+05 1.644619e+05 1.702064e+05 1.769127e+05 1.842622e+05 ds trend ... multiplicati... -136073.190485
4 77084 96043.833333 97957.250000 101216.833333 104458.750000 105968.083333 109260.000000 1.127021e+05 1.193099e+05 1.231274e+05 1.239627e+05 1.281134e+05 1.262742e+05 1.232700e+05 122815.083333 115972.916667 114768.250000 125350.833333 1.396642e+05 1.535522e+05 1.617357e+05 1.673551e+05 1.741188e+05 1.823445e+05 ds trend ... multiplicati... -135463.986688
In [0]: