Notes

main_aype.py


# author : makcin

# Importing Libraries
import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestRegressor
import copy
from sklearn.metrics import mean_absolute_error
import openpyxl
from datetime import date, timedelta
from sklearn.linear_model import HuberRegressor, LinearRegression, TheilSenRegressor, RANSACRegressor
from sklearn.linear_model import Ridge, Lasso
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.linear_model import ElasticNetCV
from sklearn.linear_model import ElasticNet
from sklearn.utils.validation import check_consistent_length, check_array
pd.set_option('display.max_rows', 6000)
from scripts import _check_reg_targets,mean_absolute_percentage_error,best_model_pipeline
import warnings
warnings.filterwarnings("ignore")
import re
from openpyxl import load_workbook
from datetime import datetime


# ------- AYPE Models --------------------

# 1- AYPE MS Prediction Model

# Data Çekme kodu ile değişecek

df_org = pd.read_excel("AYPE_Data_08082022.xlsx",index_col = 0,engine='openpyxl')


df_org.rename(columns = {'1201.1FI2_0210.DACA.PV':'AYPE1_Etilen_Capacity',
'1201.2FI2_0210.DACA.PV':'AYPE2_Etilen_Capacity',
'1201.0FI5_0902.DACA.PV':'AYPE_MS_Import',
'5801.11MBL01CT001_XQ60':'Ambient_Temperature',
'1201.1PIC1_0243.DACA.PV':'AYPE1_Reaktor_Basinci',
'1201.2PIC1_0243.DACA.PV':'AYPE2_Reaktor_Basinci',
'1201.0FI5_0901.DACA.PV': 'AYPE_HS_Import',
'1201.0FI5_0903.DACA.PV': 'AYPE_LS_Import'}, inplace = True)

df_aype = copy.deepcopy(df_org)

# Confidence 0 olan dataları veri setinden düşürmek.
df_aype_manipulated = copy.deepcopy(df_aype)

confidence_cols = list([col for col in df_aype_manipulated.columns if 'Confidence' in col])

for i in confidence_cols:
df_aype_manipulated.drop(
df_aype_manipulated.loc[(df_aype_manipulated[i] == 0)].index,
inplace=True)

df_aype_manipulated.drop(confidence_cols,axis=1,inplace=True)

# Sıfırdan küçük değerlerin sıfıra eşitlenmesi

main_features = list(df_aype_manipulated.columns)

main_features.remove('Ambient_Temperature')

for i in main_features:
df_aype_manipulated.loc[df_aype_manipulated[i] < 0, i] = 0

df_aype_manipulated.loc[df_aype_manipulated['Ambient_Temperature']<=-10,'Ambient_Temperature'] = -10

# Reaktör basıncı durumuna göre kapasite değerlerinin düzenlenmesi

df_aype_manipulated.loc[df_aype_manipulated['AYPE1_Reaktor_Basinci']<=1000,'AYPE1_Etilen_Capacity'] = 0
df_aype_manipulated.loc[df_aype_manipulated['AYPE2_Reaktor_Basinci']<=1000,'AYPE2_Etilen_Capacity'] = 0


df_aype_manipulated.drop(df_aype_manipulated.loc[(df_aype_manipulated['AYPE1_Reaktor_Basinci'] <=1000) & (df_aype_manipulated['AYPE1_Etilen_Capacity'] <= 9000)].index,inplace=True)
df_aype_manipulated.drop(df_aype_manipulated.loc[(df_aype_manipulated['AYPE2_Reaktor_Basinci'] <=1000) & (df_aype_manipulated['AYPE2_Etilen_Capacity'] <= 9000)].index,inplace=True)


# Ek feature'lar eklenmesi

df_aype_manipulated['Total_capacity_kg/h'] = df_aype_manipulated['AYPE1_Etilen_Capacity'] + df_aype_manipulated['AYPE2_Etilen_Capacity']

target_aype_ms_import_model = 'AYPE_MS_Import'

df_aype_manipulated.drop(df_aype_manipulated.loc[((df_aype_manipulated['Total_capacity_kg/h'] >=20000) & (df_aype_manipulated[target_aype_ms_import_model] <=4.5))].index,inplace=True)


print(df_aype_manipulated)

# Model datasının hazırlanması (kullanılmayacak feature'lar çıkarılmalı)


df_aype_ms_import_model = df_aype_manipulated[['AYPE1_Etilen_Capacity', 'AYPE2_Etilen_Capacity',
'AYPE_MS_Import','Ambient_Temperature','Total_capacity_kg/h']]

df_aype_ms_import_model = df_aype_ms_import_model.dropna()


# Model kodları

df_aype_ms_import_model_df = df_aype_ms_import_model[['AYPE1_Etilen_Capacity','AYPE2_Etilen_Capacity','AYPE_MS_Import']]


# Model Pipeline with GridSearchCV

result_aype_ms_prediction = best_model_pipeline(n=100,df=df_aype_ms_import_model_df,target=target_aype_ms_import_model,name_of_model='AYPE_MS_Import_Model')

# Model sonuçları Excel'e yazılıyor.

n = (len(result_aype_ms_prediction) - 2)/2

model_pred_aype_ms_import_model = round(result_aype_ms_prediction[0], 2)

model_intercept_aype_ms_import_model = round(result_aype_ms_prediction[1], 2)

values_used_in_aype_ms_import_model = [round(num, 2) for num in result_aype_ms_prediction[int(-n):]]

model_coefs_of_aype_ms_import_model = [round(num, 2) for num in result_aype_ms_prediction[2:int(2+n)]]

# Arom FG Prediction Model Sonuçları Excel'e yazılıyor.

wb = load_workbook('Draft_Final_Output.xlsx')

main_summary_sheet = wb['Main_Summary_Sheet']

main_summary_sheet['D9'] = values_used_in_aype_ms_import_model[0]

main_summary_sheet['D10'] = values_used_in_aype_ms_import_model[1]


aype_sheet = wb['AYPE']

aype_sheet['B3'] = values_used_in_aype_ms_import_model[0]

aype_sheet['B4'] = values_used_in_aype_ms_import_model[1]

aype_sheet['D3'] = model_coefs_of_aype_ms_import_model[0]

aype_sheet['D4'] = model_coefs_of_aype_ms_import_model[1]

aype_sheet['B5'] = model_intercept_aype_ms_import_model

aype_sheet['L2'] = model_pred_aype_ms_import_model

aype_sheet['R1'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")



wb.save(r'C:Usersmert.akcinDesktopDaily NG DemandNG_Demand_NewNg_Demand_Prod_CodeDraft_Final_Output.xlsx')
wb.close()