I have the following dataset:
data = {
'date': ['1/1/2019', '1/2/2019', '1/3/2019', '1/4/2019', '1/1/2019', '1/2/2019', '1/3/2019', '1/4/2019'],
'account_id': [1, 1, 1, 1, 2, 2, 2, 2],
'value_1': [1, 2, 3, 4, 5, 6, 7, 8],
'value_2': [1, 3, 6, 9, 10, 12, 14, 16]
}
df = pd.DataFrame(data,index = data['date']).drop('date', 1)
df
What I need is to extrapolate value 1 and value 2 forward by 30 days.
I came across Extrapolate Pandas DataFrame . It would work beautifully if there were no duplicated entries in the date column.
I thought of using sth of this sort but I don't understand how to add v to the function:
def extrapolation(df):
extend = 1
y = pd.DataFrame(
data=df,
index=pd.date_range(
start=df.index[0],
periods=len(df.index) + extend
)
)
#then, the extrapolation piece
df_out=df.head(0).copy()
for k,v in df.groupby('account_id'):
df_out=pd.concat([df_out,extrapolation(df)])
You can modify the linked answer as follows:
def extrapolate(df):
new_max = df.index.max() + pd.to_timedelta('30D')
dates = pd.date_range(df.index.min(), new_max, freq='D')
ret_df = df.reindex(dates)
x = np.arange(len(df))
# new x values
new_x = pd.Series(np.arange(len(ret_df)), index=dates)
for col in df.columns:
fit = np.polyfit(x, df[col], 1)
# tranform and fill
ret_df[col].fillna(fit[0]*new_x + fit[1], inplace=True)
return ret_df
and then apply:
ext_cols = ['value_1', 'value_2']
df.groupby('account_id')[ext_cols].apply(extrapolate)
You can also specify the polynomial orders for each column:
poly_orders = [1,2]
ext_cols = ['value_1', 'value_2']
def extrapolate(df):
new_max = df.index.max() + pd.to_timedelta('30D')
dates = pd.date_range(df.index.min(), new_max, freq='D')
ret_df = df.reindex(dates)
x = np.arange(len(df))
# new x values
new_x = pd.Series(np.arange(len(ret_df)), index=dates)
for col, o in zip(ext_cols, poly_orders):
fit = np.polyfit(x, df[col], o)
print(fit)
# tranform and fill
new_vals = pd.Series(0, index=dates)
for i in range(1,o+1):
new_vals = new_x**i * fit[o-i]
ret_df[col].fillna(new_vals, inplace=True)
return ret_df
And use sklearn.linear_model.LinearRegression
for better manipulation of input/output instead of numpy.polyfit
.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.