oscar-defelice

 poetry add llvmlite -vvv --lock 
Using virtualenv: /Users/oscardefelice/miniconda3/envs/tempr
PyPI: No release information found for llvmlite-0.1, skipping
PyPI: 45 packages found for llvmlite *
Using version ^0.39.0 for llvmlite

Updating dependencies
Resolving dependencies...
   1: fact: dataflows is 0.1.0
   1: derived: dataflows

oscar-defelice

[tool.poetry]
name = "dataflows"
version = "0.1.0"
description = ""
authors = ["oscar de felice <oscar@tempr.ai>"]

[tool.poetry.dependencies]
python = ">=3.9, <3.10"
kedro = "0.18.1"
dask = {extras = ["distributed"], version = "^2021.12.0"}

oscar-defelice

FROM tiangolo/uvicorn-gunicorn-fastapi:python3.7
WORKDIR /app
COPY . /app

ENV MODEL_FOLDER=/app/model

RUN pip install -r requirements.txt

# copy project
COPY ./model/ ${MODEL_FOLDER}

oscar-defelice

from datetime import datetime
from typing import List, Optional
from pydantic import BaseModel

# Inputs
class InputData(BaseModel):
    """
        An object to define the input data for the price estimator model.
        It contains the features we want to use to get a prediction.
    """

oscar-defelice

{
  "data": "data.json",
  "train_test_ratio": 0.2,
  "normalise": true,
  "pretrained_model": null,
  "model_config": {
         "model_name": "house_pricing_model",
         "layers": {
                  "first_layer": 64, 
                  "second_layer": 64,

oscar-defelice

# estimator.py
import click

from utils import read_config, train

@click.command()
@click.argument('operation')
@click.option('--conf', type=click.Path(exists=True))
def main(operation, conf):
    click.echo(f"{operation} started")

oscar-defelice

import tensorflow as tf
from tensorflow.keras.models import load_model Sequential
from tensorflow.keras.layers import Dense

import json
import numpy as np
from sklearn.model_selection import train_test_split

def read_config(config_file_path):
    with open(config_file_path, 'r') as f:

oscar-defelice

import os
import json

from .regressor import PriceEstimator

MODEL_FOLDER = os.getenv("MODEL_FOLDER")
ESTIMATOR = PriceEstimator.from_pretrained(MODEL_FOLDER)

def get_predictions(X):
        return ESTIMATOR.predict(X)

oscar-defelice

import numpy as np
from sklearn.model_selection import train_test_split

config = {
           'data': data,
           'train_test_ratio': 0.2 
          }

def feature_selection(data):
  """

oscar-defelice

import os
from tensorflow.keras.models import load_model
from .services import 

class PriceEstimator:
    """
        PriceEstimator object to collect prediction methods to be accessed
        by API services.
    """