oscar-defelice

from fastapi import FastAPI, HTTPException

from ai.services import get_predictions
from core import config
from schemas.schemas import InputData, ResponseDataAPI

app = FastAPI(title=config.PROJECT_NAME, version=config.VERSION, openapi_url="/v1/openapi.json")


@app.get("/status")

oscar-defelice

config = {
           'data': data,
           'train_test_ratio': 0.2,
           'model_config': {
               'model_name': 'house_pricing_model',
               'layers': {
                        'first_layer': 12, 
                        'second_layer': 5, 
                        'output_layer': 1
                       },

oscar-defelice

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout

num_features = X_train.shape[1]

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

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

from sklearn.model_selection import train_test_split

X = pd.DataFrame(np.c_[df[df.columns[:-1]]], columns = df.columns[:-1])
Y = df.target

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state=42)

oscar-defelice

correlation_matrix = df.corr().round(2)
# annot = True to print the values inside the square
sns.heatmap(data=correlation_matrix, annot=True);

oscar-defelice

import seaborn as sns
import matplotlib.pyplot as plt

# seaborn histogram
sns.distplot(boston_dataset.target, hist=True, kde=True, 
             bins=30, color = 'blue',
             hist_kws={'edgecolor':'black'})
# Add labels
plt.title('Histogram of target variable')
plt.xlabel('House examples')

oscar-defelice

# your client is so famous that has a dataset already in sklearn
from sklearn.datasets import load_boston
boston_dataset = load_boston()

df = pd.DataFrame(boston_dataset.data, columns=boston_dataset.feature_names)

oscar-defelice

async function predict() {
    const predictedClass = tf.tidy(() => {
      const text = document.getElementById("myText").value;
      const tokenisation = tokenise(text, word2index);
      const predictions = model.predict(tf.tensor2d(tokenisation, [1, maxLen]));
      return predictions.as1D().argMax();
    });
const classId = (await predictedClass.data())[0];
    var predictionText = "";
    switch(classId){

oscar-defelice

async function loadModel() {
  const model = await tf.loadLayersModel(modelPath);
  return model;
}