Python yhat.Yhat类代码示例

def home():
    if request.method == 'POST':
        yh = Yhat("[email protected]", "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)

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)

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)

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)

        {"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())
    

    @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)

 """ 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("[email protected]", "b36b987283a83e5e4d2814af6ef0eda9", "http://cloud.yhathq.com/")
 yh.deploy("Final_Recommender", Final_Recommender, globals()) 

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)

    "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")

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]

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)

        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"

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())

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)