def errorCorrectionForecast(preds, prices,companies):
"""
:type preds: pd.DataFrame
:type prices: pd.DataFrame
:type companies: list
:rtype analystGrades: DataFrame
:rtype forecastFAll: {}
"""
preds.sort_values(by=['MONTH'],inplace=True)
forecastFAll = {}
analystGrades = pd.DataFrame(columns=['ESTIMID','ALYSNAM','GRADES','GRADE','DATES','IDENTITY'])
analystGrades.set_index('ESTIMID',inplace=True)
analystGrades= analystGrades.fillna(value=0)
analystGrades[['GRADES','DATES']].astype(object)
for company in companies:
forecastC = pd.DataFrame(columns=['COMPANY', 'FORECAST', 'OFFSET'],
index=range(MONTH_BEG, MONTH_END))
forecastC.index.name = 'MONTH'
forecastFAll[company] = forecastC
for month in range(MONTH_BEG,MONTH_END):
xit.progressRatio(month, MONTH_END - MONTH_BEG, "Offset Corrector forecast", 10)
(analystGrades, preds, forecastFAll) = step(preds, prices, analystGrades, forecastFAll, month)
return analystGrades, preds, forecastFAll
def evaluateForecast(forecast, prices):
sum = 0
pointNb = 0
for i, pred in forecast.iterrows():
try:
xit.progressRatio(i, len(forecast), "Forecast evaluation", 10)
except:
pass
try:
priceLine = prices.loc[i]
#priceLine = prices.loc[int(pred['MONTH'])]
price = priceLine['PRC']
except:
continue
forecasted = pred['FORECAST']
if forecasted == 0 or forecasted is None:
continue
deviation = abs(price - forecasted) / price
sum += deviation
pointNb += 1
if pointNb != 0:
sum /= pointNb
else:
return 0
return sum
def evaluateForecast(forecast, prices):
for i, pred in forecast.iterrows():
xit.progressRatio(i, len(forecast), "Forecast evaluation", 10)
try:
priceLine = prices.loc[int(pred['MONTH'])]
except:
continue
if len(priceLine) == 1:
price = priceLine['PRC']
forecasted = pred['FORECAST']
deviation = abs(price - forecasted) / price
forecast.set_value(i, 'GRADE', deviation)
forecast.set_value(i, 'OFFSET', price - forecasted)
return forecast
def evaluateSinglePredictions(company, preds, prices):
grades = pd.DataFrame(columns=[
'COMPANY', 'MONTH', 'PREDNO', 'ESTIMID', 'ALYSNAM', 'FORECAST', 'GRADE'
],
index=range(len(preds)),
dtype=float)
totalPred = len(preds)
for i, row in preds.iterrows():
val, date = grade(preds, prices, i)
if val != -1:
grades.loc[i] = [
row['XCOMPANY'], date, 0, row['ESTIMID'], row['ALYSNAM'],
row['VALUE'], val
]
else:
preds.set_value(i, 'GRADE', val)
xit.progressRatio(i, totalPred, "Pred analysis", 2)
xit.progressRatio(totalPred, totalPred, "Pred analysis completed", 2)
grades = grades.dropna()
return grades
def price_forecast(grades, company):
forecast = pd.DataFrame(columns=[
'COMPANY', 'MONTH', 'FORECAST', 'GRADE', 'BEST_FORECAST',
'STRAIGHT_FORECAST'
])
minMonth = int(grades['MONTH'].min())
maxMonth = int(grades['MONTH'].max())
for monthEstimation in range(minMonth, maxMonth):
xit.progressRatio(monthEstimation - minMonth, maxMonth - minMonth,
"Forecast", 10)
maskGradesMonth = (grades['COMPANY'] == company) & (
grades['MONTH'] > monthEstimation - 5) & (grades['MONTH'] <=
monthEstimation + 5)
preds = grades.loc[maskGradesMonth]
totalWeightMonth = 0
totalWeightMonthB = 0
weightedVals = []
weightedValsB = []
for j, pred in preds.iterrows():
currentMonth = pred['MONTH']
currentWeight = gauss_function(currentMonth, 1, monthEstimation,
2) * pred['GRADE']
weightedVal = currentWeight * pred['FORECAST']
currentWeightB = indicatrice_function(currentMonth,
monthEstimation)
weightedValB = currentWeightB * pred['FORECAST']
totalWeightMonth += currentWeight
totalWeightMonthB += currentWeightB
weightedVals.append(weightedVal)
weightedValsB.append(weightedValB)
if totalWeightMonth > 0:
estimation = sum(weightedVals) / totalWeightMonth
estimationB = sum(weightedValsB) / totalWeightMonthB
else:
estimation = 0
estimationB = 0
# Best forecast
bestForecast = estimation
worstForecast = estimation
maskGradesMonth = (grades['COMPANY'] == company) & (grades['MONTH']
== monthEstimation)
thisMonth = preds.loc[maskGradesMonth]
if len(thisMonth) > 0:
index = thisMonth['GRADE'].argmax()
bestForecast = preds.loc[index]['FORECAST'].item()
index = thisMonth['GRADE'].argmin()
worstForecast = preds.loc[index]['FORECAST'].item()
forecast.loc[len(forecast)] = [
company, monthEstimation, estimation, 0, bestForecast, estimationB
]
return forecast