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)
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"})
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"]
})
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)
#!/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)
return X
def predict(self, data):
pred = self.clf.predict(data).tolist()
return pred
clf = pickle.load(open('./yhat/test/decisiontree.model', 'rb'))
xtrain = pickle.load(open('./yhat/test/xtrain.model', 'rb'))
myTree = DecisionTreePML(clf=clf, xtrain=xtrain)
pp.pprint(yh.upload("chTestTree", myTree))
print yh.predict("chTestTree", 2, [2, 3, 2, 4, 2, 3, 2])
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)
from yhat import Yhat
import string
import pandas as pd
yh = Yhat("colin", "d325fc5bcb83fc197ee01edb58b4b396",
"https://sandbox.c.yhat.com/")
filename = "http://yhat-data.s3.amazonaws.com/beer_reviews.csv"
df = pd.read_csv(filename)
printable = set(string.printable)
df.beer_name = df.beer_name.map(lambda y: filter(lambda x: x in printable, y))
for row in df.beer_name.unique():
data = {"beers": [row]}
try:
result = yh.predict("BeerRecommender", data)['result']
print(result[:5])
except:
pass
img = np.array(img)
s = img.shape[0] * img.shape[1]
img_wide = img.reshape(1, s)
return self.pca.transform(img_wide[0])
def predict(self, data):
preds = self.knn.predict(data)
preds = np.where(preds==1, "check", "drivers_license")
pred = preds[0]
return {"image_label": pred}
img_clf = ImageClassifier(pca=pca, knn=knn, STANDARD_SIZE=STANDARD_SIZE)
# authenticate
yh = Yhat("YOUR USERNAME", "YOUR API KEY")
# upload model to yhat
yh.upload("imageClassifier", img_clf)
#call the api w/ some example data
# this one is a drivers license
new_image = open("dl16.jpeg", 'rb').read()
import base64
#we need to make the image JSON serializeable
new_image = base64.encodestring(new_image)
print yh.predict("imageClassifier", version=4, data=new_image)
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))
return sorted(results, key=lambda x: x[2])
#Deploy to Yhat
yh = Yhat("{USERNAME}", "{APIKEY}")
br = BeerRec(simple_distances=simple_distances,
beers=beers,
udfs=[calc_distance])
yh.deploy("PydataBeerRec", br)
#Test it Out
yh.predict("PydataBeerRec", 1, {
"beer": "Coors Light",
"weights": [1, 1, 1, 1]
})
yh.predict("PydataBeerRec", 1, {
"beer": "Coors Light",
"weights": [2, 1, 0, 0]
})
from yhat import Yhat
import string
import pandas as pd
yh = Yhat("colin", "d325fc5bcb83fc197ee01edb58b4b396", "https://sandbox.c.yhat.com/")
filename = "http://yhat-data.s3.amazonaws.com/beer_reviews.csv"
df = pd.read_csv(filename)
printable = set(string.printable)
df.beer_name = df.beer_name.map(lambda y: filter(lambda x: x in printable, y))
for row in df.beer_name.unique():
data = { "beers": [row] }
try:
result = yh.predict("BeerRecommender", data)['result']
print(result[:5])
except:
pass
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]
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))
return sorted(results, key=lambda x: x[2])
#Deploy to Yhat
yh = Yhat("{USERNAME}", "{APIKEY}")
br = BeerRec(simple_distances=simple_distances, beers=beers,
udfs=[calc_distance])
yh.deploy("PydataBeerRec", br)
#Test it Out
yh.predict("PydataBeerRec", 1, {"beer": "Coors Light", "weights": [1, 1, 1, 1]})
yh.predict("PydataBeerRec", 1, {"beer": "Coors Light", "weights": [2, 1, 0, 0]})