Learn by Coding Examples in Applied Machine Learning

Machine Learning algorithm Pipeline in Python using scikit-learn?

In [8]:
# ignore warnings
import warnings
warnings.filterwarnings("ignore")

Machine Learning pipeline that standardizes the data then creates a model

In [9]:
# Create a pipeline that standardizes the data then creates a model
import pandas as pd
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

# load data
filename = 'pima.indians.diabetes.data.csv'

names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']

dataframe = pd.read_csv(filename, names=names)
print(); print(dataframe.head())

array = dataframe.values
X = array[:,0:8]
Y = array[:,8]

# create pipeline
estimators = []
estimators.append(('standardize', StandardScaler()))
estimators.append(('lda', LinearDiscriminantAnalysis()))

model = Pipeline(estimators)

# evaluate pipeline
seed = 7
kfold = KFold(n_splits=10, random_state=seed)

results = cross_val_score(model, X, Y, cv=kfold)

print(); print("Accuracy Results: ")
print(results.mean())

   preg  plas  pres  skin  test  mass   pedi  age  class
0     6   148    72    35     0  33.6  0.627   50      1
1     1    85    66    29     0  26.6  0.351   31      0
2     8   183    64     0     0  23.3  0.672   32      1
3     1    89    66    23    94  28.1  0.167   21      0
4     0   137    40    35   168  43.1  2.288   33      1

Accuracy Results: 
0.773462064251538

Machine Learning pipeline that extracts features from the data then creates a model

In [10]:
# Create a pipeline that extracts features from the data then creates a model
import pandas as pd
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.pipeline import Pipeline
from sklearn.pipeline import FeatureUnion
from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA
from sklearn.feature_selection import SelectKBest

# load data
filename = 'pima.indians.diabetes.data.csv'

names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']

dataframe = pd.read_csv(filename, names=names)
print(); print(dataframe.head())

array = dataframe.values
X = array[:,0:8]
Y = array[:,8]

# create feature union
features = []
features.append(('pca', PCA(n_components=3)))
features.append(('select_best', SelectKBest(k=6)))
feature_union = FeatureUnion(features)

# create pipeline
estimators = []
estimators.append(('feature_union', feature_union))
estimators.append(('logistic', LogisticRegression()))

model = Pipeline(estimators)

# evaluate pipeline
seed = 7

kfold = KFold(n_splits=10, random_state=seed)
results = cross_val_score(model, X, Y, cv=kfold)

print(); print("Accuracy Results: ")
print(results.mean())

   preg  plas  pres  skin  test  mass   pedi  age  class
0     6   148    72    35     0  33.6  0.627   50      1
1     1    85    66    29     0  26.6  0.351   31      0
2     8   183    64     0     0  23.3  0.672   32      1
3     1    89    66    23    94  28.1  0.167   21      0
4     0   137    40    35   168  43.1  2.288   33      1

Accuracy Results: 
0.7760423786739576
In [ ]: