Marvin Engine Example Code

marvin_example.py

// Data Acquisitor
from marvin_python_toolbox.common.data import MarvinData
import pandas as pd

file_path = MarvinData.download_file(url="https://s3.amazonaws.com/marvin-engines-data/Iris.csv")

iris = pd.read_csv(file_path)
iris.drop('Id',axis=1,inplace=True)

marvin_initial_dataset = iris

// Training Preparator
from sklearn.cross_validation import train_test_split

train, test = train_test_split(marvin_initial_dataset, test_size = 0.3)

train_X = train[['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm']]
train_y = train.Species

test_X = test[['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm']]
test_y =test.Species

marvin_dataset = {'train_X': train_X, 'train_y': train_y, 'test_X': test_X, 'test_y': test_y}

// Model Traning
from sklearn import svm

clf = svm.SVC()
model = clf.fit(marvin_dataset['train_X'], marvin_dataset['train_y'])

marvin_model = model

// Model Evaluation
from sklearn.metrics import accuracy_score

predicted = marvin_model.predict(marvin_dataset['test_X'])
metric = accuracy_score(marvin_dataset['test_y'], predicted)

marvin_metrics = metric

// Prediction Preparator
input_message = ['12', '34', '10', '23']

// Predictor
final_prediction = marvin_model.predict(input_message)[0]