Sandy4321

plt.figure(figsize=(10,5))
sns.scatterplot(data=df_scatter, x='Click Activation Rate', y='Activation Rate', s=200, color='#2653de')

for line in range(0, df_scatter.shape[0]):
     plt.text(df_scatter['Click Activation Rate'][line]+0.001, df_scatter['Activation Rate'][line], 
     df_scatter['Channel'][line], horizontalalignment='left', 
     size='medium', color='black', weight='semibold')

Sandy4321

def expected_steps(df):    
    Q = df.drop(
        ['Null', 'Activation'], axis=1).drop(['Null', 'Activation'], axis=0)

    I = np.identity(Q.shape[1])

    N = np.linalg.inv(I - Q.to_numpy())
    
    t = np.sum(N, axis=1)
    

Sandy4321

python -m predict.test_predict \
--csv-data-path gs://${PROJECT_ID}-black-friday-demo-bucket/data/test.csv \
--model-name black_friday_forecast \
--project-id ${PROJECT_ID} \
--version-name $VERSION

Sandy4321

from setuptools import setup, find_packages

REQUIREMENTS = [
    "scikit-learn",
    "pandas",
    "numpy",
    "tensorflow==1.15.0",
    "gcsfs",
    "google-api-python-client"
]

Sandy4321

PROJECT_ID=<PROJECT_ID>
BUCKET_NAME="${PROJECT_ID}-black-friday-demo-bucket"
MODEL_NAME=black_friday_forecast
REGION=us-central1
VERSION='v'`date '+%Y%m%d_%H%M%S'`
MODEL_PATH=gs://$BUCKET_NAME/models/$VERSION/model
PACKAGE_PATH=gs://$BUCKET_NAME/models/$VERSION/package/black_friday_forecast-0.0.1.tar.gz

# Package solution
python setup.py sdist

Sandy4321

# -*- coding: utf-8 -*-

import argparse
import datetime
import pandas as pd
import os


from sklearn import preprocessing
from sklearn.metrics import mean_squared_error, make_scorer

Sandy4321

PROJECT_ID=<PROJECT_ID>
BUCKET_NAME="${PROJECT_ID}-black-friday-demo-bucket"
MODEL_NAME=black_friday_forecast
REGION=us-central1
VERSION='v'`date '+%Y%m%d_%H%M%S'`
MODEL_PATH=gs://$BUCKET_NAME/models/$VERSION/model

gcloud ai-platform jobs submit training black_friday_forecast_$(date +"%Y%m%d_%H%M%S") \
  --job-dir gs://$BUCKET_NAME/models/$VERSION/job_dir \
  --package-path ./train \

Sandy4321

import googleapiclient.discovery
import argparse
import pandas as pd
import json

import logging
logging.basicConfig()
logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)

Sandy4321

import pandas as pd
import numpy as np

from sklearn.base import BaseEstimator
from sklearn import preprocessing
import json


class BlackFridayPreprocess(BaseEstimator):

Sandy4321

from sklearn.ensemble import RandomForestRegressor
from train.models.custom_transformers import BlackFridayPreprocess, BlackFridayIdTransformer, BlackFridayLabelEncoder
from sklearn.pipeline import Pipeline


def random_forest():
    pipeline = Pipeline(
        [
            ('preprocess', BlackFridayPreprocess()),
            ('id_filter', BlackFridayIdTransformer(