def test_detect_submodule_in_deployment(self):
yh = Yhat("greg", "test", "http://api.yhathq.com/")
_, bundle = yh.deploy("TestModel",
TestModel,
globals(),
sure=True,
dry_run=True)
self.assertEqual(len(bundle['modules']), 8)
def home():
if request.method == 'POST':
yh = Yhat("*****@*****.**", "b36b987283a83e5e4d2814af6ef0eda9", "http://cloud.yhathq.com/")
recommender_name = "Final_Recommender"
data = {"user" : request.json['user'], "products" : request.json['products'], "n": request.json['n']}
pred = yh.predict(recommender_name, data) # returns the dictionary
return Response(json.dumps(pred), mimetype='application/json')
else:
# if it is GET method, you just need to render the homepage part
# defines the jQuery pages in order to render the page in home.html template
css_url = url_for('static', filename='css/main.css')
jquery_url = url_for('static', filename='js/jquery-1.11.1.js')
# prodcuts_url = aData
products_url = url_for('static', filename='js/products.js')
highlight_url = url_for('static', filename='js/highlight.js')
main_url = url_for('static', filename='js/main.js')
return render_template('home.html', css_url=css_url,jquery_url=jquery_url, products_url=products_url,
main_url=main_url, highlight_url=highlight_url)
def index():
if request.method == 'POST':
yh = Yhat("USERNAME", "APIKEY",
"http://cloud.yhathq.com/")
pred = yh.predict("BeerRec", {"beers": request.json['beers'],
"n": request.json['n']})
return Response(json.dumps(pred),
mimetype='application/json')
else:
# static files
css_url = url_for('static', filename='css/main.css')
jquery_url = url_for('static', filename='js/jquery-1.10.2.min.js')
beers_url = url_for('static', filename='js/beers.js')
highlight_url = url_for('static', filename='js/code.js')
js_url = url_for('static', filename='js/main.js')
return render_template('index.html', css_url=css_url,
jquery_url=jquery_url, beers_url=beers_url,
js_url=js_url, highlight_url=highlight_url)
def index():
if request.method == 'POST':
yh = Yhat("USERNAME", "APIKEY", "http://cloud.yhathq.com/")
pred = yh.predict("BeerRec", {
"beers": request.json['beers'],
"n": request.json['n']
})
return Response(json.dumps(pred), mimetype='application/json')
else:
# static files
css_url = url_for('static', filename='css/main.css')
jquery_url = url_for('static', filename='js/jquery-1.10.2.min.js')
beers_url = url_for('static', filename='js/beers.js')
highlight_url = url_for('static', filename='js/code.js')
js_url = url_for('static', filename='js/main.js')
return render_template('index.html',
css_url=css_url,
jquery_url=jquery_url,
beers_url=beers_url,
js_url=js_url,
highlight_url=highlight_url)
import os
from yhat import Yhat, YhatModel, preprocess
class HelloWorld(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
me = data['name']
greeting = "Hello %s!" % me
return {"greeting": greeting}
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (
username,
apikey,
endpoint,
)
yh = Yhat(username, apikey, endpoint)
yh.deploy("HelloWorld", HelloWorld, globals(), sure=True)
def test_deployment(self):
yh = Yhat("foo", "bar", "http://api.yhathq.com/")
_, bundle = yh.deploy("HelloWorld", HelloWorld, globals(), dry_run=True)
self.assertTrue(True)
training_val = RFmodel.score(transform_dummies(X_train,False), y_train)
testing_val = RFmodel.score(transform_dummies(X_test,False), y_test)
print "training:", testing_val
print "testing: ", training_val
############ DEPLOYMENT ######################
from yhat import Yhat, YhatModel, preprocess
class TravisModel(YhatModel):
def fit_val(self):
testing_val = RFmodel.score(transform_dummies(X_test, False), y_test)
return testing_val
def execute(self,data):
data = transform_dummies(data,False)
output = RFmodel.predict(data)
return output.tolist()
########## DEPLOY SET #####################
if __name__ == '__main__':
yh = Yhat(
os.environ['YHAT_USERNAME'],
os.environ['YHAT_APIKEY'],
os.environ['YHAT_URL'],
)
yh.deploy("TravisModel", TravisModel, globals(), True)
import os
from yhat import Yhat, YhatModel, preprocess
from foo.foo import print_foo
from module import function_in_same_dir
class HelloWorld(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
me = data['name']
greeting = "Hello %s!" % me
print_foo(me)
return { "greeting": greeting, "nine": function_in_same_dir() }
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (username, apikey, endpoint,)
yh = Yhat(
username,
apikey,
endpoint
)
yh.deploy("HelloWorldPkg", HelloWorld, globals(), sure=True, verbose=1)
features = df.columns[df.columns != "MEDVALUE"]
target = "MEDVALUE"
y = df[target]
X = df.drop(target, 1)
X_train, X_test, y_train, y_test = train_test_split(X, y)
clf = linear_model.LinearRegression()
clf.fit(X_train,y_train)
y_pred = clf.predict(X_test)
print r2_score(y_test, y_pred)
from yhat import Yhat, YhatModel, preprocess, df_to_json
class HousePred(YhatModel):
@preprocess(in_type=pd.DataFrame, out_type=pd.DataFrame)
def execute(self, data):
result = clf.predict(data[features])
df = pd.DataFrame(data={'predicted_price': result})
return df
yh = Yhat(
"YHAT_USERNAME",
"YHAT_APIKEY",
"http://cloud.yhathq.com/")
yh.deploy("HouseValuePredictor", HousePred, globals())
print df_to_json(df[:1])
# create and train a classifier
nbayes = MultinomialNB(fit_prior=False)
nbayes.fit(train_twitter_tfidf, train.liked_content.tolist())
# prep the test data, then create a confusion matrix to examine the results
test_twitter_tfidf = vec.transform(test.text)
preds = nbayes.predict(test_twitter_tfidf)
print pd.crosstab(test.liked_content, preds)
from yhat import Yhat, YhatModel, preprocess
class TwitterRanker(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
tweet = data['tweet_content']
data = vec.transform([tweet])
pred = nbayes.predict(data)
prob = nbayes.predict_proba(data)
prob = {
"ham": round(prob[0][0], 4),
"spam": 1 - round(prob[0][0], 4)
}
return {"pred": pred[0], "prob": prob}
yh = Yhat("YOUR_USERNAME", "YOUR_APIKEY", "http://cloud.yhathq.com/")
yh.deploy("twitterRanker", TwitterRanker, globals())
{"name": "x", "na_filler": 0},
{"name": "z", "na_filler": fill_z}
]
class MyOtherClass:
def hello(self, x):
return "hello: %s" % str(x)
REQS = open("reqs.txt").read()
### <DEPLOYMENT START> ###
# @preprocess(in_type=dict, out_type=pd.DataFrame, null_handler=features)
class MyModel(YhatModel):
REQUIREMENTS=REQS
@preprocess(out_type=pd.DataFrame)
def execute(self, data):
return predict(data)
# "push" to server would be here
data = {"x": 1, "z": None}
if __name__ == '__main__':
creds = credentials.read()
yh = Yhat(creds['username'], creds['apikey'], "http://localhost:3000/")
yh.deploy("mynewmodel", MyModel, globals())
iris = load_iris()
X = pd.DataFrame(iris.data, columns=iris.feature_names)
y = pd.DataFrame(iris.target, columns=["flower_types"])
clf = SVC()
clf.fit(X, y["flower_types"])
class MySVC(YhatModel):
@preprocess(in_type=pd.DataFrame, out_type=pd.DataFrame)
def execute(self, data):
prediction = clf.predict(pd.DataFrame(data))
species = ['setosa', 'versicolor', 'virginica']
result = [species[i] for i in prediction]
return result
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (
username,
apikey,
endpoint,
)
yh = Yhat(username, apikey, endpoint)
yh.deploy("SupportVectorClassifier", MySVC, globals(), sure=True)
data = pd.DataFrame(data)
data = data[features]
prob = glm.predict_proba(data)[0][1]
if prob > 0.3:
decline_code = "Credit score too low"
else:
decline_code = ""
odds = glm.predict_log_proba(data)[0][1]
score = calculate_score(odds)
output = {
"prob_default": [prob],
"decline_code": [decline_code],
"score": [score]
}
return output
df_term[features].head()
test = {
"last_fico_range_low": 705,
"last_fico_range_high": 732,
"home_ownership": "MORTGAGE"
}
LoanModel().execute(test)
yh = Yhat("austin", os.environ.get("SCIENCEOPS_API_KEY"), "https://sandbox.c.yhat.com/")
yh.deploy("LendingClub", LoanModel, globals(), True)
iris = load_iris()
X = pd.DataFrame(iris.data, columns=iris.feature_names)
y = pd.DataFrame(iris.target, columns=["flower_types"])
clf = SVC()
clf.fit(X, y["flower_types"])
class MySVC(YhatModel):
@preprocess(in_type=pd.DataFrame, out_type=pd.DataFrame)
def execute(self, data):
prediction = clf.predict(pd.DataFrame(data))
species = ['setosa', 'versicolor', 'virginica']
result = [species[i] for i in prediction]
return result
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (username, apikey, endpoint,)
yh = Yhat(
username,
apikey,
endpoint
)
yh.deploy("SupportVectorClassifier", MySVC, globals(), sure=True)
features = [{"name": "x", "na_filler": 0}, {"name": "z", "na_filler": fill_z}]
class MyOtherClass:
def hello(self, x):
return "hello: %s" % str(x)
REQS = open("reqs.txt").read()
### <DEPLOYMENT START> ###
# @preprocess(in_type=dict, out_type=pd.DataFrame, null_handler=features)
class MyModel(YhatModel):
REQUIREMENTS = REQS
@preprocess(out_type=pd.DataFrame)
def execute(self, data):
return predict(data)
# "push" to server would be here
data = {"x": 1, "z": None}
if __name__ == '__main__':
creds = credentials.read()
yh = Yhat(creds['username'], creds['apikey'], "http://localhost:3000/")
yh.deploy("mynewmodel", MyModel, globals())
features = df.columns[df.columns != "MEDVALUE"]
target = "MEDVALUE"
y = df[target]
X = df.drop(target, 1)
X_train, X_test, y_train, y_test = train_test_split(X, y)
clf = linear_model.LinearRegression()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print r2_score(y_test, y_pred)
from yhat import Yhat, YhatModel, preprocess, df_to_json
class HousePred(YhatModel):
@preprocess(in_type=pd.DataFrame, out_type=pd.DataFrame)
def execute(self, data):
result = clf.predict(data[features])
df = pd.DataFrame(data={'predicted_price': result})
return df
yh = Yhat("YHAT_USERNAME", "YHAT_APIKEY", "http://cloud.yhathq.com/")
yh.deploy("HouseValuePredictor", HousePred, globals())
print df_to_json(df[:1])
import time
from yhat import Yhat
# cd ~/repos/yhat/demos/heroku-demos/demo-lending-club/model
df = pd.read_csv("./model/LoanStats3a.csv", skiprows=1)
df_head = df.head()
def is_poor_coverage(row):
pct_null = float(row.isnull().sum()) / row.count()
return pct_null < 0.8
df_head[df_head.apply(is_poor_coverage, axis=1)]
df = df[df.apply(is_poor_coverage, axis=1)]
df['year_issued'] = df.issue_d.apply(lambda x: int(x.split("-")[0]))
df_term = df[df.year_issued < 2012]
features = ['last_fico_range_low', 'last_fico_range_high', 'home_ownership']
yh = Yhat("demo-master", "3b0160e10f6d7a94a2528b11b1c9bca1", "https://sandbox.c.yhat.com/")
for i, row in df_term[features][:500].iterrows():
# some models require vectorized data, others don't
# non-vectorized
# row = row.to_dict() # {'is_rent': True, 'last_fico_range_low': 785, 'last_fico_range_high': 789}
# vectorized
row = { k: [v] for k,v in row.to_dict().items() } # {'is_rent': [True], 'last_fico_range_low': [785], 'last_fico_range_high': [789]}
print yh.predict("LendingClub", row)
time.sleep(.05)
{
's1':1, 's2':1, 's3':1, 's4':1, 's5':1,
'w1':1, 'w2':1, 'w3':1, 'w4':1,
'k1':1, 'k2':1, 'k3':1, 'k4':1, 'k5':1,
'k6':1, 'k7':1, 'k8':1, 'k9':1, 'k10':1,
'k11':1, 'k12':1, 'k13':1, 'k14':1, 'k15':1
}
test_data = pd.read_csv(open('data/test.csv', 'r'), quotechar='"')
sub_data = pd.read_csv(open('data/sampleSubmission.csv', 'r'), quotechar='"')
if not np.alltrue(test_data['id'] == sub_data['id']):
raise Exception("IDs do not match")
yh = Yhat(username, apikey)
variabless = sub_data.columns[1:]
raw_tweets = test_data['tweet'].tolist()
for variable in variables:
model_version = best_model[variable]
model_name = "TweetClassifier_%s" % (variable, )
results_from_server = yh.raw_predict(model_name, model_version, raw_tweets)
pred = results_from_server['prediction']['scores']
sub_data[variable] = pred
try:
sub_data.to_csv(open(sub_file, 'w'), index=False)
except IOError:
sys.stderr.write("IO error: could not write data to file")
#!/usr/bin/env python
from flask import Flask, request, render_template, url_for, Response, json
from yhat import Yhat
import os
app = Flask(__name__)
yh = Yhat(os.environ.get("YHAT_USERNAME"), os.environ.get("YHAT_APIKEY"), os.environ.get("YHAT_URL"))
@app.route('/', methods=['GET', 'POST'])
def index():
if request.method == 'POST':
# print request.json['beers']
try:
pred = yh.predict("BeerRecommender", {"beers": request.json['beers'],
"n": request.json['n']})
return Response(json.dumps(pred), mimetype='application/json')
except Exception, e:
print e
return Response(json.dumps({"error": str(e)}),
mimetype='application/json')
else:
# static files
css_url = url_for('static', filename='css/main.css')
jquery_url = url_for('static', filename='js/jquery-1.10.2.min.js')
beers_url = url_for('static', filename='js/beers.js')
highlight_url = url_for('static', filename='js/code.js')
js_url = url_for('static', filename='js/main.js')
return render_template('index.html', css_url=css_url,
jquery_url=jquery_url, beers_url=beers_url,
js_url=js_url, highlight_url=highlight_url)
import os
import subprocess
from yhat import Yhat, YhatModel, preprocess
class HelloWorld(YhatModel):
# ensure the environment has "tree"
subprocess.check_output(["tree"])
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
me = data['name']
greeting = "Hello %s!" % me
return { "greeting": greeting }
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (username, apikey, endpoint,)
yh = Yhat(
username,
apikey,
endpoint
)
yh.deploy("PyAptGet", HelloWorld, globals(), sure=True, packages=["tree"])
from yhat import Yhat, YhatModel, preprocess
import os
USERNAME = os.environ["USERNAME"]
APIKEY = os.environ["APIKEY"]
URL = os.environ["URL"]
class HelloWorld(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
me = data['name']
greeting = "Hello " + str(me) + "!"
return {"greeting": greeting}
yh = Yhat(USERNAME, APIKEY, URL)
yh.deploy("Gitmodel", HelloWorld, globals(), True)
class CurrencyPortfolio(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
P = matrix(data['risk_aversion'] * returns_cov.as_matrix())
q = matrix(-exp_returns['mean'].as_matrix())
G = matrix(0.0, (len(q),len(q)))
G[::len(q)+1] = -1.0
h = matrix(0.0, (len(q),1))
A = matrix(1.0, (1,len(q)))
b = matrix(1.0)
solution = solvers.qp(P, q, G, h, A, b)
expected_return = exp_returns['mean'].dot(solution['x'])[0]
variance = sum(solution['x'] * returns_cov.as_matrix().dot(solution['x']))[0]
investments = {}
for i, amount in enumerate(solution['x']):
# Ignore values that appear to have converged to 0.
if amount > 10e-5:
investments[countries[i]] = amount*100
return {
'risk_aversion': data['risk_aversion'],
'investments': investments,
'expected_return': expected_return,
'variance': variance
}
yh = Yhat('USERNAME', 'APIKEY', 'http://cloud.yhathq.com/')
yh.deploy('CurrencyPortfolio', CurrencyPortfolio, globals())
product - a product id (integer)
"""
p = dists[products].apply(lambda row: np.sum(row), axis=1)
p = p.order(ascending=False)
return p.index[p.index.isin(products) == False]
get_sims(["Sierra Nevada Pale Ale", "120 Minute IPA", "Stone Ruination IPA"])
from yhat import Yhat, YhatModel, preprocess
class BeerRecommender(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
beers = data.get("beers")
suggested_beers = get_sims(beers)
result = []
for beer in suggested_beers:
result.append({"beer": beer})
return result
yh = Yhat("YOUR_USERNAME", "YOUR_APIKEY", "http://cloud.yhathq.com/")
if raw_input("Deploy? (y/N)") == "y":
print yh.deploy("BeerRecommender", BeerRecommender, globals())
print yh.predict("BeerRecommender", {"beers": ["Sierra Nevada Pale Ale",
"120 Minute IPA", "Stone Ruination IPA"]})
def is_poor_coverage(row):
pct_null = float(row.isnull().sum()) / row.count()
return pct_null < 0.8
df_head[df_head.apply(is_poor_coverage, axis=1)]
df = df[df.apply(is_poor_coverage, axis=1)]
df['year_issued'] = df.issue_d.apply(lambda x: int(x.split("-")[0]))
df_term = df[df.year_issued < 2012]
features = ['last_fico_range_low', 'last_fico_range_high', 'home_ownership']
yh = Yhat("demo-master", "3b0160e10f6d7a94a2528b11b1c9bca1",
"https://sandbox.c.yhat.com/")
for i, row in df_term[features][:500].iterrows():
# some models require vectorized data, others don't
# non-vectorized
# row = row.to_dict() # {'is_rent': True, 'last_fico_range_low': 785, 'last_fico_range_high': 789}
# vectorized
row = {
k: [v]
for k, v in row.to_dict().items()
} # {'is_rent': [True], 'last_fico_range_low': [785], 'last_fico_range_high': [789]}
print yh.predict("LendingClub", row)
time.sleep(.05)
class ChurnModel(YhatModel):
# Type casts incoming data as a dataframe
@preprocess(in_type=pd.DataFrame, out_type=pd.DataFrame)
def execute(self, data):
# Collect customer meta data
response = data[['Area Code', 'Phone']]
charges = ['Day Charge', 'Eve Charge', 'Night Charge', 'Intl Charge']
response['customer_worth'] = data[charges].sum(axis=1)
# Convert yes no columns to bool
data[yes_no_cols] = data[yes_no_cols] == 'yes'
# Create feature space
X = data[features].as_matrix().astype(float)
X = scaler.transform(X)
# Make prediction
churn_prob = clf.predict_proba(X)
response['churn_prob'] = churn_prob[:, 1]
# Calculate expected loss by churn
response['expected_loss'] = response['churn_prob'] * response[
'customer_worth']
response = response.sort('expected_loss', ascending=False)
# Return response DataFrame
return response
yh = Yhat("e[at]yhathq.com", " MY APIKEY ", "http://cloud.yhathq.com/")
print "Deploying model"
response = yh.deploy("PythonChurnModel", ChurnModel, globals())
print json.dumps(response, indent=2)
return p[0:n_recs]
get_sims(["Sierra Nevada Pale Ale", "60 Minute IPA"])
from yhat import Yhat, YhatModel, preprocess
class BeerRecommender(YhatModel):
REQUIREMENTS=['numpy==1.11.3',
'pandas==0.19.2',
'scikit-learn==0.18.1']
def execute(self, data):
beers = data.get("beers")
n_recs = data.get("n_recs")
prob = data.get("prob")
unique = data.get("unique")
suggested_beers = get_sims(beers, n_recs, prob, unique)
result = suggested_beers.to_dict(orient='records')
return result
model = BeerRecommender()
model.execute({'beers':["Sierra Nevada Pale Ale"],'n_recs':10})
yh = Yhat("colin", "ce796d278f4840e30e763413d8b4baa4", "http://do-sb-dev-master.x.yhat.com/")
print yh.deploy("BeerRecommender", BeerRecommender, globals(), autodetect=False, sure=True)
# print yh.predict("BeerRecommender", {"beers": ["Sierra Nevada Pale Ale",
# "120 Minute IPA", "Stone Ruination IPA"]})
import base64
def transform(self, data):
image_string = data["image_string"]
STANDARD_SIZE = (50, 50)
f = StringIO(base64.decodestring(image_string))
img = Image.open(f)
img = img.getdata()
img = img.resize(STANDARD_SIZE)
img = map(list, img)
img = np.array(img)
s = img.shape[0] * img.shape[1]
img_wide = img.reshape(1, s)
return img_wide[0]
def predict(self, img):
x = self.pca.transform([img])
x = self.std_scaler.transform(x)
results = {"label": self.clf.predict(x)[0]}
probs = {"prob_" + str(i) : prob for i, prob in enumerate(self.clf.predict_proba(x)[0])}
results['probs'] = probs
return results
digit_model = DigitModel(clf=clf, std_scaler=std_scaler, pca=pca)
yh = Yhat("YOUR USERNAME", "YOUR APIKEY", "http://cloud.yhathq.com/")
yh.deploy("digitRecognizer", digit_model)
data = data[features]
prob = glm.predict_proba(data)[0][1]
if prob > 0.3:
decline_code = "Credit score too low"
else:
decline_code = ""
odds = glm.predict_log_proba(data)[0][1]
score = calculate_score(odds)
output = {
"prob_default": [prob],
"decline_code": [decline_code],
"score": [score]
}
return output
df_term[features].head()
test = {
"last_fico_range_low": 705,
"last_fico_range_high": 732,
"home_ownership": "MORTGAGE"
}
LoanModel().execute(test)
yh = Yhat("colin", "d325fc5bcb83fc197ee01edb58b4b396",
"https://sandbox.c.yhat.com/")
yh.deploy("LendingClub", LoanModel, globals(), True)
def parse_tweet(tweet):
trees = nltk.ne_chunk(nltk.pos_tag(nltk.word_tokenize(tweet)))
for tree in trees.subtrees():
etype = None
if tree.node == "PERSON":
etype = "PERSON"
elif tree.node == "GPE":
etype = "PLACE"
if etype is not None:
ne = " ".join([leaf[0] for leaf in tree.leaves()])
tweet = tweet.replace(ne,
"<" + etype + ">" + ne + "</" + etype + ">")
return tweet
class Tagger(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, raw):
tweet = raw['text']
tagged = parse_tweet(tweet)
raw['tagged'] = tagged
return raw
tg = Tagger()
yh = Yhat("greg", "mykey", YHAT_URL)
print yh.deploy("NamedEntityTagger" + str(i), Tagger, globals())
def convert_prob_to_score(p):
"""
takes a probability and converts it to a score
Example:
convert_prob_to_score(0.1)
> 340
"""
odds = (1 - p) / p
return np.log(odds) * (40 / np.log(2)) + 340
##Deploying to Yhat
from yhat import BaseModel, Yhat
yh = Yhat("greg", "abcd1234")
class LoanModel(BaseModel):
def transform(self, newdata):
df = pd.DataFrame(newdata)
# handle nulls here
# df['monthly_income'] = self.income_imputer.predict(df[[]])
df['number_of_dependents'] = df['number_of_dependents'].fillna(0)
return df
def predict(self, df):
data = df[self.features]
result = {}
p = self.clf.predict_proba(data)
p = p[::, 1]
return self.dv.transform(doc)
def predict(self, x):
"""
Evaluate model on array
delegates to LinearRegression self.lr
returns a dict (will be json encoded) suppling
"predictedPrice", "suspectedOutlier", "x", "threshold"
where "x" is the input vector and "threshold" is determined
whether or not a listing is a suspected outlier.
"""
doc = self.dv.inverse_transform(x)[0]
predicted = self.lr.predict(x)[0]
err = abs(predicted - doc["price"])
return {
"predictedPrice": predicted,
"x": doc,
"suspectedOutlier": 1 if (err > self.threshold) else 0,
"threshold": self.threshold,
}
pm = PricingModel(dv=dv, lr=LR, threshold=np.percentile(trainingErrs, 95))
print pm.execute(testing.T.to_dict()[0])
if raw_input("Deploy? (y/N): ").lower() == "y":
username = "******"
apikey = "abcd1234"
yh = Yhat(username, apikey, "http://cloud.yhathq.com/")
print yh.deploy(model_name, fitted_model)
pred[np.where(pred < 0.0)] = 0.0
return {"scores" : pred}
train_data = pd.read_csv(open('data/train.csv','r'),quotechar='"')
raw_tweets = train_data['tweet'].tolist()
sanity_raw = raw_tweets[:100]
sentiments = train_data.columns[4:].tolist()
vectorizer = CountVectorizer(tokenizer=nltk.word_tokenize,
stop_words='english',
max_features=3000,
binary=True,
ngram_range=(1,1))
yh = Yhat(username,apikey)
X_train = vectorizer.fit_transform(raw_tweets)
for sentiment in sentiments:
print "Processing '%s'" % sentiment
clf = SVR()
y_train = train_data[sentiment].tolist()
print "Training classifier"
clf.fit(X_train,y_train)
tweet_clf = TweetClassifier(clf=clf,vectorizer=vectorizer)
model_name = "TweetClassifier_%s" % (sentiment,)
print "Uploading to yhat"
red_upper = np.array([50, 56, 200], dtype = "uint8")
mask = cv2.inRange(image, red_lower, red_upper)
output = cv2.bitwise_and(image, image, mask = mask)
output_gray = rgb2gray(output)
total_red = np.sum(output_gray)
y, x = ndimage.center_of_mass(output_gray)
data = {
"x": x,
"y": y,
"xmax": output_gray.shape[1],
"ymax": output_gray.shape[0],
"total_red": total_red,
"time": time.time()
}
return data
from yhat import Yhat, YhatModel
class DroneModel(YhatModel):
REQUIREMENTS = [
"opencv"
]
def execute(self, data):
return get_coords(data['image64'])
yh = Yhat(username, apikey, url)
yh.deploy("DroneModel", DroneModel, globals(), True)
from yhat import Yhat, BaseModel
def hello():
return "HEY AUSTIN!"
class MyModel(BaseModel):
def require(self):
pass
def transform(self, data):
return "something"
def predict(self, data):
return data * 10
mm = MyModel(clf=range(10), udfs=[hello])
yh = Yhat("greg", "abcd1234")
yh.upload("functest", mm)
import os
from yhat import Yhat, YhatModel, preprocess
class HelloWorld(YhatModel):
version = os.environ["MODEL_VERSION"]
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
me = data['name']
greeting = "Hello %s!" % me
print os.environ["MODEL_VERSION"]
return { "greeting": greeting }
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (username, apikey, endpoint,)
yh = Yhat(
username,
apikey,
endpoint
)
yh.deploy("HelloWorldVer", HelloWorld, globals(), sure=True)
import json
import pickle
import time
# raw_data = [[ 0., 0., 5., 13., 9., 1., 0., 0.],
# [ 0., 0., 13., 15., 10., 15., 5., 0.],
# [ 0., 3., 15., 2., 0., 11., 8., 0.],
# [ 0., 4., 12., 0., 0., 8., 8., 0.],
# [ 0., 5., 8., 0., 0., 9., 8., 0.],
# [ 0., 4., 11., 0., 1., 12., 7., 0.],
# [ 0., 2., 14., 5., 10., 12., 0., 0.],
# [ 0., 0., 6., 13., 10., 0., 0., 0.]]
# yh = Yhat("greg", "fCVZiLJhS95cnxOrsp5e2VSkk0GfypZqeRCntTD1nHA", "http://localhost:5000/")
yh = Yhat("clotheshorse", "gwAaXlkkIyasM2ue7iwjUmuoUKCodSZjobNU9a5WmKc", "http://166.78.26.170/")
# yh = Yhat("greg", "fCVZiLJhS95cnxOrsp5e2VSkk0GfypZqeRCntTD1nHA", "http://54.235.251.150/")
# # pp.pprint(skd.show_models())
# # print "*"*80
# s = time.time()
# pp.pprint(yh.raw_predict('gregsTree_v11', [2, 3, 2, 2]))
# print time.time() - s
# # print "*"*80
# # pp.pprint(skd.predict('digits', raw_data))
# # print "*"*80
class DecisionTreePML(BaseModel):
def transform(self, rawData):
pair = [5, 3]
self.hprint2('<div id="lineCanvas" style="overflow: auto; position:relative;height:300px;width:400px;"></div>')
self.hprint2('<script type="text/javascript">')
self.hprint2('var g = new line_graph();')
for i in range(len(parcoh)):
self.hprint2("g.add('%d', %f);"%(i+1, parcoh[i]*100))
self.hprint2('g.render("lineCanvas", "Paragraphs");')
self.hprint2('</script>')
# display text annotation/highlight
met(d, is_local=is_local, num_label=max(int(good), int(bad)), label_sent=True)
self.fout.write("<hr>")
self.fout.write("<label><h2>Cohesion Highlighter</h2></label>")
if int(good)>0:
self.fout.write('<span class="bold red">Red: Cohesive </span>')
if int(bad)>0:
self.fout.write('<span class="yellow-background">Yellow: Not Cohesive</span>')
self.hprint2('<div style="width:600px;"><p align="left">')
d.print_html(self.fout, int(good), int(bad))
self.hprint2('</p></div>')
# End Computing and OUtput
output = self.fout.getvalue()
self.fout.close()
return { "html_output": output }
#StickyTextYhat().run()
yh = Yhat("*****@*****.**", "ff7bb725be9e4a32af286f464b316a23", "http://umsi.yhathq.com/")
yh.deploy ("StickyText", StickyTextYhat, globals())
"k10": 1,
"k11": 1,
"k12": 1,
"k13": 1,
"k14": 1,
"k15": 1,
}
test_data = pd.read_csv(open("data/test.csv", "r"), quotechar='"')
sub_data = pd.read_csv(open("data/sampleSubmission.csv", "r"), quotechar='"')
if not np.alltrue(test_data["id"] == sub_data["id"]):
raise Exception("IDs do not match")
yh = Yhat(username, apikey)
variabless = sub_data.columns[1:]
raw_tweets = test_data["tweet"].tolist()
for variable in variables:
model_version = best_model[variable]
model_name = "TweetClassifier_%s" % (variable,)
results_from_server = yh.raw_predict(model_name, model_version, raw_tweets)
pred = results_from_server["prediction"]["scores"]
sub_data[variable] = pred
try:
sub_data.to_csv(open(sub_file, "w"), index=False)
except IOError:
sys.stderr.write("IO error: could not write data to file")
def execute(self, data):
P = matrix(data['risk_aversion'] * returns_cov.as_matrix())
q = matrix(-exp_returns['mean'].as_matrix())
G = matrix(0.0, (len(q), len(q)))
G[::len(q) + 1] = -1.0
h = matrix(0.0, (len(q), 1))
A = matrix(1.0, (1, len(q)))
b = matrix(1.0)
solution = solvers.qp(P, q, G, h, A, b)
expected_return = exp_returns['mean'].dot(solution['x'])[0]
variance = sum(solution['x'] *
returns_cov.as_matrix().dot(solution['x']))[0]
investments = {}
for i, amount in enumerate(solution['x']):
# Ignore values that appear to have converged to 0.
if amount > 10e-5:
investments[countries[i]] = amount * 100
return {
'risk_aversion': data['risk_aversion'],
'investments': investments,
'expected_return': expected_return,
'variance': variance
}
yh = Yhat('USERNAME', 'APIKEY', 'http://cloud.yhathq.com/')
yh.deploy('CurrencyPortfolio', CurrencyPortfolio, globals())
from yhat import Yhat, BaseModel
def hello():
return "HEY AUSTIN!"
class MyModel(BaseModel):
def require(self):
pass
def transform(self, data):
return "something"
def predict(self, data):
return data * 10
mm = MyModel(clf=range(10), udfs=[hello])
yh = Yhat("greg", "abcd1234")
print yh._extract_source("model", mm)
import os
from yhat import Yhat, YhatModel, preprocess
from foo.foo import print_foo
from module import function_in_same_dir
class HelloWorld(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
me = data['name']
greeting = "Hello %s!" % me
print_foo(me)
return {"greeting": greeting, "nine": function_in_same_dir()}
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (
username,
apikey,
endpoint,
)
yh = Yhat(username, apikey, endpoint)
yh.deploy("HelloWorldPkg", HelloWorld, globals(), sure=True, verbose=1)
"""
p = dists[products].apply(lambda row: np.sum(row), axis=1)
p = p.order(ascending=False)
return p.index[p.index.isin(products)==False]
class BeerRecommender(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
# handle uft8 beer names
beers = [beer.encode('utf8') for beer in data.get("beers", [])]
suggested_beers = get_sims(beers)
result = []
for beer in suggested_beers:
result.append({"beer": beer})
return result
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (username, apikey, endpoint,)
yh = Yhat(
username,
apikey,
endpoint
)
yh.deploy("BeerRecommender", BeerRecommender, globals(), sure=True)
""" YAHOO """
yahoo_data = aData
yahoo_data.sort(columns = 'user_id', ascending = True, inplace = True) # no pass by value
# rating-based CF recommendations
data = {'user': [15], 'products':[123764, 71142], 'n':10}
aGraphlab_Model = Graphlab_Recommender(dataset = yahoo_data)
print aGraphlab_Model.predict(data)
""" USA TODAY """
# rating-based CF recommendations
usaToday_data = aData
param = {'user_id':'Reviewer', 'product_id':'Id', 'ratings': 'Rating'}
data = {'user': ['Edna Gundersen'], 'products':[123901], 'n':10}
aGraphlab_Model = Graphlab_Recommender(dataset = usaToday_data, needed_param = param)
print aGraphlab_Model.predict(data)
# textual analytics + CF method
param = {'comment': 'Brief', 'ratings': 'Rating', 'user_id':'Reviewer', 'product_id':'Id'}
model, ratings_data = rec.sentiment_analysis_regress(usaToday_data, param)
ratings_data = ratings_data.sort(columns = 'user_id')
ratings_data['user_id'] = ratings_data['user_id'].fillna('anonymous')
print ratings_data
aGraphlab_Model = Graphlab_Recommender(dataset = ratings_data)
data = {'user': ['Edna Gundersen'], 'products':[123901], 'n':10}
print aGraphlab_Model.predict(data)
'''
# deployment
yh = Yhat("*****@*****.**", "b36b987283a83e5e4d2814af6ef0eda9", "http://cloud.yhathq.com/")
yh.deploy("Final_Recommender", Final_Recommender, globals())
class ChurnModel(YhatModel):
@preprocess(in_type=pd.DataFrame, out_type=pd.DataFrame)
def execute(self, data):
response = pd.DataFrame(data)
charges = ['day_charge', 'eve_charge', 'night_charge', 'intl_charge']
response['customer_worth'] = data[charges].sum(axis=1)
# Convert yes no columns to bool
data[yes_no_cols] = data[yes_no_cols] == 'yes'
# Create feature space
X = data[features].as_matrix().astype(float)
X = scaler.transform(X)
# Make prediction
churn_prob = clf.predict_proba(X)
response['churn_prob'] = churn_prob[:, 1]
# Calculate expected loss by churn
response['expected_loss'] = response['churn_prob'] * response[
'customer_worth']
response = response.sort('expected_loss', ascending=False)
response = response[['customer_worth', 'churn_prob', 'expected_loss']]
# Return response DataFrame
return response
yh = Yhat(raw_input("Yhat username: "******"Yhat apikey: "),
"http://sandbox.yhathq.com/")
print "Deploying model"
response = yh.deploy("PythonChurnModel", ChurnModel, globals())
print df_to_json(churn_df[:1])
@preprocess(in_type=pd.DataFrame,out_type=pd.DataFrame)
def execute(self,data):
# Collect customer meta data
response = data[['Area Code','Phone']]
charges = ['Day Charge','Eve Charge','Night Charge','Intl Charge']
response['customer_worth'] = data[charges].sum(axis=1)
# Convert yes no columns to bool
data[yes_no_cols] = data[yes_no_cols] == 'yes'
# Create feature space
X = data[features].as_matrix().astype(float)
X = scaler.transform(X)
# Make prediction
churn_prob = clf.predict_proba(X)
response['churn_prob'] = churn_prob[:,1]
# Calculate expected loss by churn
response['expected_loss'] = response['churn_prob'] * response['customer_worth']
response = response.sort('expected_loss',ascending=False)
# Return response DataFrame
return response
yh = Yhat(
"e[at]yhathq.com",
" MY APIKEY ",
"http://cloud.yhathq.com/"
)
print "Deploying model"
response = yh.deploy("PythonChurnModel",ChurnModel,globals())
print json.dumps(response,indent=2)
{"name": "x", "na_filler": 0},
{"name": "z", "na_filler": fill_z}
]
class MyOtherClass:
def hello(self, x):
return "hello: %s" % str(x)
REQS = open("reqs.txt").read()
### <DEPLOYMENT START> ###
# @preprocess(in_type=dict, out_type=pd.DataFrame, null_handler=features)
class MyModel(YhatModel):
REQUIREMENTS=REQS
@preprocess(out_type=pd.DataFrame)
def execute(self, data):
return predict(data)
# "push" to server would be here
data = {"x": 1, "z": None}
if __name__ == '__main__':
creds = credentials.read()
yh = Yhat(creds['username'], creds['apikey'])
yh.deploy_to_file("mynewmodel", MyModel, globals())
from yhat import YhatModel, Yhat, preprocess
# from first import hello as h2
import first as f2
from first import Support
from another.testfile import bye
def goodbye(y):
bye()
print y, "goodbye!"
class Example(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
goodbye(x)
return Support().hello(10)
# return h2(data)
from first import x
yh = Yhat("greg", "fCVZiLJhS95cnxOrsp5e2VSkk0GfypZqeRCntTD1nHA",
"http://api.yhathq.com/")
yh.deploy_to_file("Example", Example, globals())
from yhat import Yhat, YhatModel , preprocess
class HelloWorld(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
me = data['name']
greeting = "Hello " + str(me) + "!"
return { "greeting": greeting }
yh = Yhat("*****@*****.**", "ff7bb725be9e4a32af286f464b316a23", "http://umsi.yhathq.com/")
yh.deploy ("HelloWorld", HelloWorld, globals())
get_sims(["Sierra Nevada Pale Ale", "120 Minute IPA", "Coors Light"])
# Index([u'Samuel Adams Boston Lager', u'Sierra Nevada Celebration Ale', u'90 Minute IPA', u'Arrogant Bastard Ale', u'Stone IPA (India Pale Ale)', u'60 Minute IPA', u'HopDevil Ale', u'Stone Ruination IPA', u'Sierra Nevada Bigfoot Barleywine Style Ale', u'Storm King Stout', u'Samuel Adams Winter Lager', u'Samuel Adams Summer Ale', u'Prima Pils', u'Anchor Steam Beer', u'Old Rasputin Russian Imperial Stout', u'Samuel Adams Octoberfest', ...], dtype='object')
from yhat import Yhat, YhatModel, preprocess
class BeerRecommender(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
beers = data.get("beers")
suggested_beers = get_sims(beers)
result = []
for beer in suggested_beers:
result.append({"beer": beer})
return result
BeerRecommender().execute({
"beers":
["Sierra Nevada Pale Ale", "120 Minute IPA", "Stone Ruination IPA"]
})
yh = Yhat("USERNAME", "APIKEY", "http://cloud.yhathq.com")
yh.deploy("BeerRecommender", BeerRecommender, globals())
yh.predict("BeerRecommender", {
"beers":
["Sierra Nevada Pale Ale", "120 Minute IPA", "Stone Ruination IPA"]
})
import os
from yhat import Yhat, YhatModel
from pricing import Pricing
class MarketingSearchAPI(YhatModel):
REQUIREMENTS = ["pandas==0.15.2", "numpy"]
def execute(self, data):
result = p.predict(data)
return result
p = Pricing()
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (
username,
apikey,
endpoint,
)
yh = Yhat(username, apikey, endpoint)
yh.deploy("RelayRidesPricing", MarketingSearchAPI, globals(), sure=True)
beer = raw_data['beer']
weights = raw_data.get("weights", [1, 1, 1, 1])
# normalize the weights so they sum to 1.0
weights = [float(w) / sum(weights) for w in weights]
print "making recs for: " + beer
return (beer, weights)
def predict(self, data):
beer, weights = data
results = []
for beer_cmp in self.beers:
if beer!=beer_cmp:
dist = calc_distance(self.simple_distances, beer, beer_cmp, weights)
results.append((beer, beer_cmp, dist))
dists = sorted(results, key=lambda x: x[2])
# return dists
return normalize_dists(dists)
yh = Yhat({USERNAME}, {APIKEY})
myBeerModel = BeerRec(simple_distances=simple_distances, beers=beers,
udfs=[calc_distance, normalize_dists])
if raw_input("Deploy? (y/N)")=="y":
print yh.deploy("BeerRec", myBeerModel)
print yh.predict("BeerRec", None, {"beer": "Coors Light"})
# 1 4.9 3.0 1.4
# 2 4.7 3.2 1.3
y = pd.DataFrame(iris.data[:,3:4], columns=iris.feature_names[3:4])
# petal width (cm)
# 0 0.2
# 1 0.2
# 2 0.2
regr = linear_model.LinearRegression()
regr.fit(X, y)
class LinReg(YhatModel):
@preprocess(in_type=pd.DataFrame, out_type=pd.DataFrame)
def execute(self, data):
prediction = regr.predict(pd.DataFrame(data))
return prediction
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (username, apikey, endpoint,)
yh = Yhat(
username,
apikey,
endpoint
)
yh.deploy("LinearRegression", LinReg, globals(), sure=True)
features = [{"name": "x", "na_filler": 0}, {"name": "z", "na_filler": fill_z}]
class MyOtherClass:
def hello(self, x):
return "hello: %s" % str(x)
REQS = open("reqs.txt").read()
### <DEPLOYMENT START> ###
# @preprocess(in_type=dict, out_type=pd.DataFrame, null_handler=features)
class MyModel(YhatModel):
REQUIREMENTS = REQS
@preprocess(out_type=pd.DataFrame)
def execute(self, data):
return predict(data)
# "push" to server would be here
data = {"x": 1, "z": None}
if __name__ == '__main__':
creds = credentials.read()
yh = Yhat(creds['username'], creds['apikey'])
yh.deploy_to_file("mynewmodel", MyModel, globals())
#!/usr/bin/env python
from yhat import Yhat
#yh = Yhat("*****@*****.**", "RoVGt5VDZfHkdBLx2rre76sg998cD4IuJiYzzNmNp48")
yh = Yhat("*****@*****.**", "HaDobDyJtFoQQPZ9xRkCJrI44OB6EW8hC6IfUMsGzo8")
checkoo_models = yh.show_models()
for model in checkoo_models['models']:
print model
newcase = {
'loc':'BeiJing',
'major':'Computer Science/Engineering',
'vtype':'F1',
'ventry':'New',
'byear':'2013',
'bmonth':'7',
'bday':'20'
}
checkoo_version = 14
print yh.predict('CKModel',checkoo_version,newcase)
import os
from yhat import Yhat, YhatModel, preprocess
class HelloWorld(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
me = data['name']
greeting = "Hello %s!" % me
return { "greeting": greeting }
username = os.environ["USERNAME"]
apikey = os.environ["APIKEY"]
endpoint = os.environ["OPS_ENDPOINT"]
print "%s:%s:%s" % (username, apikey, endpoint,)
yh = Yhat(
username,
apikey,
endpoint
)
yh.deploy("IndentedModel", HelloWorld, globals(), sure=True)
def transform(self, data):
image_string = data["image_string"]
STANDARD_SIZE = (50, 50)
f = StringIO(base64.decodestring(image_string))
img = Image.open(f)
img = img.getdata()
img = img.resize(STANDARD_SIZE)
img = map(list, img)
img = np.array(img)
s = img.shape[0] * img.shape[1]
img_wide = img.reshape(1, s)
return img_wide[0]
def predict(self, img):
x = self.pca.transform([img])
x = self.std_scaler.transform(x)
results = {"label": self.clf.predict(x)[0]}
probs = {
"prob_" + str(i): prob
for i, prob in enumerate(self.clf.predict_proba(x)[0])
}
results['probs'] = probs
return results
digit_model = DigitModel(clf=clf, std_scaler=std_scaler, pca=pca)
yh = Yhat("YOUR USERNAME", "YOUR APIKEY", "http://cloud.yhathq.com/")
yh.deploy("digitRecognizer", digit_model)
from yhat import Yhat, YhatModel, preprocess
x = range(10)
class HelloWorld(YhatModel):
@preprocess(in_type=dict, out_type=dict)
def execute(self, data):
print x[:10]
me = data['name']
greeting = "Hello " + str(me) + "!"
return {"greeting": greeting, "x": x}
# yh = Yhat("greg", "fCVZiLJhS95cnxOrsp5e2VSkk0GfypZqeRCntTD1nHA", "http://cloud.yhathq.com/")
yh = Yhat("greg", "9207b9a2dd9d48848b139b729d4354bc", "http://localhost:8080/")
yh.deploy("NewZippedModel", HelloWorld, globals())
#!/usr/bin/env python
from flask import Flask, request, render_template, url_for, Response, json
from yhat import Yhat
from uuid import uuid4
import numpy as np
from bandits import EpsilonGreedy
app = Flask(__name__)
yh = Yhat("__username__", "__apikey__", "http://cloud.yhathq.com/")
arms = ["EuclideanBeerRec", "CosineBeerRec", "CorrelationBeerRec"]
eg = EpsilonGreedy(3)
ids = {}
@app.route('/', methods=['GET', 'POST'])
def index():
if request.method == 'POST':
arm = eg.choose_arm()
arm_name = arms[arm]
u_id = str(uuid4())
pred = yh.predict(arm_name, {"beers": request.json['beers']})
ids[u_id] = {'arm': arm, 'arm_name': arm_name}
return Response(json.dumps({
'result': pred['result'],
'uid': u_id
}),
mimetype='application/json')
else: