Skip to content
Snippets Groups Projects
Select Git revision
  • 345418521e5ee89f8156255d8cdcbd8132895c53
  • main default protected
2 results

compute_missing.py

Blame
    • compute_missing.py 2.54 KiB
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    24
    25
    26
    27
    28
    29
    30
    31
    32
    33
    34
    35
    36
    37
    38
    39
    40
    41
    42
    43
    44
    45
    46
    47
    48
    49
    50
    51
    52
    53
    54
    55
    56
    57
    58
    59
    60
    61
    62
    63
    64
    65
    66
    67
    68
    69
    70
    71
    72
    73
    74
    75
    76
    77
    78
    79
    80
    81
    82
    83
    84 
    

    

    

    # -*- coding: utf-8 -*-
"""
Created on Fri Feb 26 12:58:53 2021

@author: Christoph

"""
import pandas as pd
import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from sklearn.model_selection import train_test_split
np.random.seed(42)

data = pd.read_csv('data_unfilled.csv')
data= data.iloc[:,1:]

#komplette Daten fürs Training:
data_cmpl = data.loc[data['Streckenvorhersage.Dauer']!= 0]
X_cmpl = data_cmpl[['Streckenvorhersage.ZielortID','Streckenvorhersage.StartortID','time']]
Y_cmpl = data_cmpl['Streckenvorhersage.Dauer']
X_cmpl_train, X_cmpl_test, y_cmpl_train, y_cmpl_test = train_test_split(X_cmpl, Y_cmpl, test_size=0.2)


# fehlende Daten für Test:
data_incmpl = data.loc[data['Streckenvorhersage.Dauer']== 0]
X_incmpl = data_incmpl[['Streckenvorhersage.ZielortID','Streckenvorhersage.StartortID','time']]
Y_incmpl = data_incmpl['Streckenvorhersage.Dauer']


#Prediction anhand vorhandener Daten


myANN = Sequential()
myANN.add(Dense(80, activation='relu', input_dim=X_cmpl.shape[1]))
myANN.add(Dense(50,activation='relu'))
myANN.add(Dense(30,activation='relu'))
myANN.add(Dense(1,activation='linear'))
myANN.compile(loss='mean_squared_error', optimizer='adam')

myANN.fit(X_cmpl_train,y_cmpl_train, epochs=100,shuffle=True,verbose=False)
yp = myANN.predict(X_cmpl_test)
yp=np.squeeze(yp)

yDiff = yp - y_cmpl_test
print('Mittlere Abweichung auf fehlende Daten: %e ' % (np.mean(np.abs(yDiff))))



#impute Dauer auf vorhandenen Daten
yp = myANN.predict(X_incmpl)
yp=np.squeeze(yp)
Y_incmpl = pd.DataFrame(data=yp,columns=['Streckenvorhersage.Dauer'])


X_train, X_test, y_train, y_test = train_test_split(X_cmpl, Y_cmpl, test_size=0.35)
y_train = pd.DataFrame(data=y_train,columns=['Streckenvorhersage.Dauer'])

X_train=X_train.append(X_incmpl)
y_train=pd.concat([y_train,Y_incmpl])


myANN = Sequential()
myANN.add(Dense(80, activation='relu', input_dim=X_cmpl.shape[1]))
myANN.add(Dense(50,activation='relu'))
myANN.add(Dense(30,activation='relu'))
myANN.add(Dense(1,activation='linear'))
myANN.compile(loss='mean_squared_error', optimizer='adam')

myANN.fit(X_train,y_train, epochs=100,shuffle=True,verbose=False)
yp = myANN.predict(X_test)
yp=np.squeeze(yp)

yDiff = yp - y_test
print('Mittlere Abweichung mit aufgefüllten Daten(simuliert): %e ' % (np.mean(np.abs(yDiff))))


y_test = pd.DataFrame(data=y_test,columns=['Streckenvorhersage.Dauer'])
X_all=X_train.append(X_test)
y_all=pd.concat([y_train,y_test])
data= X_all
y_all= np.asarray(y_all)
data['Streckenvorhersage.Dauer']=y_all
data.to_csv('data_filled(ANN).csv')

    Impressum Datenschutzerklärung