def modeled_indices(X, y, df, model_type= None):
'''
We get the largest negatives residuals here
INPUT Feature matrix, Labels ie price_filtering, Specify which model
OUTPUT Sorted residuals from the specified modeled (largest negatives first)
'''
#Manual override option
if model_type:
model = {'L1': Lasso(alpha= 1, tol= .01, warm_start= False, positive= False),
'SVR_lin': SVR('linear', C= 6.3095734448019298, gamma= 0.1, degree= 1),
'RF': RandomForestRegressor(min_samples_split= 2, n_estimators= 10)}
y_hat = model[model_type].fit(X, y).predict(X)
else:
model = search_best_params(X, y, df)
y_hat = model.fit(X, y).predict(X)
#Used for later for identifying 2stds
df['predicted_price'] = y_hat
df['residual'] = df['px'] - df['predicted_price']
#Residual as a percentage
# df['price_distance_craig'] = 1 - df['px'] / df['predicted_price']
#change specifically so we could show in terms of stand deviation vs percentage
df['price_distance_craig'] = df['residual'] / df['residual'].std()
return df, find_indices(y_hat, y), model
def routine(X, y, model, df, pxs):
'''
INPUT Feature Matrix, labels, Original DataFrame, eBay prices
OUTPUT Recommendation Table (Ranked respectively)
'''
# this should be in some proportion to the sample size
top_n_recs = int(len(df) * .15)
if top_n_recs < 10: raise Exception("too few observations")
top_indices = find_indices(model.fit(X, y).predict(X), y)
df = df.iloc[top_indices][['heading', 'year', 'px']][:top_n_recs]
max_price = make_pricing_panel(df, pxs)['spread'].max()
average_spread = make_pricing_panel(df, pxs)['spread'].mean()
return max_price, average_spread
def routine(X, y, model, df, pxs):
'''
INPUT Feature Matrix, labels, Original DataFrame, eBay prices
OUTPUT Recommendation Table (Ranked respectively)
'''
# this should be in some proportion to the sample size
top_n_recs = int(len(df) * .15)
if top_n_recs < 10: raise Exception("too few observations")
top_indices = find_indices(model.fit(X, y).predict(X), y)
df = df.iloc[top_indices][['heading', 'year', 'px']][:top_n_recs]
max_price = make_pricing_panel(df, pxs)['spread'].max()
average_spread = make_pricing_panel(df, pxs)['spread'].mean()
return max_price, average_spread
