def test_plate():
ex = jarvis.Experiment('plate_demo')
ex.groundClient('git')
ones = ex.literal([1, 2, 3], "ones")
ones.forEach()
tens = ex.literal([10, 100], "tens")
tens.forEach()
@jarvis.func
def multiply(x, y):
z = x * y
print(z)
return z
doMultiply = ex.action(multiply, [ones, tens])
product = ex.artifact('product.txt', doMultiply)
product.pull()
product.plot()
#!/usr/bin/env python3
import jarvis
ex = jarvis.Experiment('twitter')
ex.groundClient('git')
training_tweets = ex.artifact('training_tweets.csv')
from clean import clean
do_tr_clean = ex.action(clean, [training_tweets])
clean_training_tweets = ex.artifact('clean_training_tweets.pkl', do_tr_clean)
from train_model import train
do_train = ex.action(train, [clean_training_tweets, 0.0001])
intermediary = ex.artifact('intermediary.pkl', do_train)
testing_tweets = ex.artifact('testing_tweets.csv')
do_te_clean = ex.action(clean, [testing_tweets])
clean_testing_tweets = ex.artifact('clean_testing_tweets.pkl', do_te_clean)
from test_model import test
do_test = ex.action(test, [intermediary, clean_testing_tweets])
model_accuracy = ex.artifact('model_accuracy.txt', do_test)
model_accuracy.pull()
model_accuracy.plot()
#!/usr/bin/env python3
import jarvis
import numpy as np
ex = jarvis.Experiment("twitter_demo")
ex.groundClient('ground')
tweets = ex.artifact('tweets.csv')
frac = ex.literal(0.75, 'frac')
split_seed = ex.literal(42, 'split_seed')
from split import split
do_split = ex.action(split, [tweets, frac, split_seed])
training_tweets = ex.artifact('training_tweets.pkl', do_split)
testing_tweets = ex.artifact('testing_tweets.pkl', do_split)
alpha = ex.literal(np.linspace(0.0, 1.0, 8).tolist(), 'alpha')
alpha.forEach()
from train_model import train
do_train = ex.action(train, [training_tweets, alpha])
model = ex.artifact('model.pkl', do_train)
from test_model import test
do_test = ex.action(test, [model, testing_tweets])
model_accuracy = ex.artifact('model_accuracy.txt', do_test)
columnArtifacts = {'model_accuracy': model_accuracy, 'model': model}
#model_accuracy.parallelPull(manifest=columnArtifacts)
import jarvis
ex = jarvis.Experiment('plate_demo')
ex.groundClient('git')
ones = ex.literal([1, 2, 3], "ones")
ones.forEach()
tens = ex.literal([10, 100], "tens")
tens.forEach()
@jarvis.func
def multiply(x, y):
z = x * y
print(z)
return z
doMultiply = ex.action(multiply, [ones, tens])
product = ex.artifact('product.txt', doMultiply)
product.parallelPull()
# product.plot()
#!/usr/bin/env python3
import jarvis
import numpy as np
with jarvis.Experiment("twitter_demo") as ex:
ex.groundClient('ground')
tweets = ex.artifact('tweets.csv')
frac = ex.literal(0.75, 'frac')
split_seed = ex.literal(42, 'split_seed')
from split import split
do_split = ex.action(split, [tweets, frac, split_seed])
training_tweets = ex.artifact('training_tweets.pkl', do_split)
testing_tweets = ex.artifact('testing_tweets.pkl', do_split)
alpha = ex.literal(np.linspace(0.0, 1.0, 8).tolist(), 'alpha')
alpha.forEach()
from train_model import train
do_train = ex.action(train, [training_tweets, alpha])
model = ex.artifact('model.pkl', do_train)
from test_model import test
do_test = ex.action(test, [model, testing_tweets])
model_accuracy = ex.artifact('model_accuracy.txt', do_test)
model_accuracy.pull()
import jarvis
with jarvis.Experiment('coarse') as ex:
ex.groundClient('ground')
@jarvis.func
def run_existing_pipeline(path_to_data, kernel):
import math
import numpy as np
import pandas as pd
from sklearn import metrics
from sklearn.svm import SVR
from sklearn.model_selection import train_test_split
def manhattan_distance(x1, y1, x2, y2):
return abs(x1 - x2) + abs(y1 - y2)
def roundtime(tstring):
hours, mins, secs = tstring.split(':')
if int(mins) >= 30:
if hours == '23':
return '00'
else:
return str(int(hours) + 1)
else:
return hours
def weekday(start):
from datetime import datetime
fmt = '%Y-%m-%d %H:%M:%S'
