cas-pml/SL/aufgaben/template/2_Code/3.1 Regression - Einfuehrung.ipynb

Feature Engineering

Klassifikation

Regression

Einleitung

In [1]:

import sys
sys.path.append('./')

In [2]:

## prepare
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
%matplotlib inline

datapath = '../3_data'
from os import chdir; chdir(datapath)

Abgrenzung gegenüber Klassifikation

(kein Code)

Das Demo Dataset: demo_data_regr.csv

In [3]:

demo_data = pd.read_csv('demo_data_regr.csv')
print(demo_data.head())

     X    y
0  6.0  2.5
1  5.1  1.9
2  5.9  2.1
3  5.6  1.8
4  5.8  2.2

In [4]:

plt.figure(figsize=(6,6))
ax = sns.scatterplot(x='X', y='y', data=demo_data)
ax.set(xlabel='X', ylabel='y');

Das Fallstudien Dataset: melb_data_prep.csv

In [5]:

data = pd.read_csv('melb_data_prep.csv')
print(data.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 18393 entries, 0 to 18392
Data columns (total 24 columns):
 #   Column                                 Non-Null Count  Dtype  
---  ------                                 --------------  -----  
 0   Rooms                                  18393 non-null  int64  
 1   Type                                   18393 non-null  int64  
 2   Price                                  18393 non-null  float64
 3   Distance                               18393 non-null  float64
 4   Bathroom                               18393 non-null  float64
 5   Car                                    18393 non-null  float64
 6   logLandsize                            18393 non-null  float64
 7   logBuildingArea                        18393 non-null  float64
 8   YearBuilt                              18393 non-null  float64
 9   CouncilArea                            18393 non-null  int64  
 10  Lattitude                              18393 non-null  float64
 11  Longtitude                             18393 non-null  float64
 12  Propertycount                          18393 non-null  float64
 13  Method_S                               18393 non-null  int64  
 14  Method_SP                              18393 non-null  int64  
 15  Method_VB                              18393 non-null  int64  
 16  Regionname_Northern_Metropolitan       18393 non-null  int64  
 17  Regionname_South_Eastern_Metropolitan  18393 non-null  int64  
 18  Regionname_Southern_Metropolitan       18393 non-null  int64  
 19  Regionname_Victoria                    18393 non-null  int64  
 20  Regionname_Western_Metropolitan        18393 non-null  int64  
 21  month                                  18393 non-null  int64  
 22  year                                   18393 non-null  int64  
 23  day_of_week                            18393 non-null  int64  
dtypes: float64(10), int64(14)
memory usage: 3.4 MB
None

Vorbereiten der Daten

In [6]:

## read and prep data
from bfh_cas_pml import prep_data, prep_demo_data
X_train, X_test, y_train, y_test = prep_data(
    'melb_data_prep.csv', 'Price', seed = 1234)

X_demo, y_demo = prep_demo_data('demo_data_regr.csv', 'y')