mmmayo13

print mldb.put('/v1/functions/fetch', {
    "type": 'fetcher',
    "params": {}
})

print mldb.put('/v1/functions/inception', {
    "type": 'tensorflow.graph',
    "params": {
        "modelFileUrl": 'archive+'+
            'http://public.mldb.ai/models/inception_dec_2015.zip'+

mmmayo13

kdNuggets = "http://www.skytree.net/wp-content/uploads/2014/08/KDnuggets.jpg"

mldb.query("SELECT inception({url: '%s'}) as *" % kdNuggets)

mmmayo13

print mldb.post("/v1/procedures", {
    "type": "import.text",
    "params": {
        "dataFileUrl": "https://public.mldb.ai/datasets/car_brand_images/cars_urls.csv",
        "outputDataset": "images"
    }
})

mldb.query("SELECT * FROM images LIMIT 3")

mmmayo13

mldb.query("SELECT count(*) FROM images GROUP BY brand")

mmmayo13

print mldb.post("/v1/procedures", {
    "type": "transform",
    "params": {
        "inputData": """
            SELECT brand,
                   inception({url}) as *
            FROM images
        """,
        "outputDataset": "training_dataset"
    }

mmmayo13

rez = mldb.post("/v1/procedures", {
    "type": "classifier.experiment",
    "params": {
        "experimentName": "car_brand_cls",
        "inputData": """        
            SELECT 
                {* EXCLUDING(brand)} as features,
                brand as label
            FROM training_dataset
        """,

mmmayo13

pd.DataFrame(runResults["confusionMatrix"])\
    .pivot_table(index="actual", columns="predicted", fill_value=0)

mmmayo13

pd.DataFrame.from_dict(runResults["labelStatistics"]).transpose()

mmmayo13

print mldb.put("/v1/functions/brand_predictor", {
    "type": "sql.expression",
    "params": {
        "expression": """
            car_brand_cls_scorer_0(
                {
                    features: inception({url})
                }) as *
        """
    }

mmmayo13

mldb.get("/v1/functions/brand_predictor/application", 
         data={'input': 
               {'url': 'http://insideevs.com/wp-content/uploads/2016/03/JL82776-750x500.jpg'}})