dipanjanS

Act as a project manager for a data science team in a tech company. 
We will be using a special notation now to indicate the flow of a data science project. 
I will provide you that notation, 
your task is to give a detailed plan for each step in the project as identified by the notation. 
Let's take an example:

Project Name: Churn Analytics for a Telecom Company

Dataset: Database with over 20000 customers data, has features including 
contract, payment method, paperless billing, monthly charges, total charges, gender, age range and of course churn (yes \ no)

dipanjanS

items_popularity = pd.read_csv('datasets/item_popularity.csv',  
                               encoding='utf-8')
items_popularity['popularity_scale_10'] = np.array(
                   np.round((items_popularity['pop_percent'] * 10)),  
                   dtype='int')
items_popularity['popularity_scale_100'] = np.array(
                  np.round((items_popularity['pop_percent'] * 100)),    
                  dtype='int')
items_popularity

dipanjanS

from sklearn.preprocessing import Binarizer

bn = Binarizer(threshold=0.9)
pd_watched = bn.transform([popsong_df['listen_count']])[0]
popsong_df['pd_watched'] = pd_watched
popsong_df.head(11)

dipanjanS

watched = np.array(popsong_df['listen_count']) 
watched[watched >= 1] = 1
popsong_df['watched'] = watched

dipanjanS

popsong_df = pd.read_csv('datasets/song_views.csv', encoding='utf-8')
popsong_df.head(10)

dipanjanS

poke_df[['HP', 'Attack', 'Defense']].describe()

dipanjanS

poke_df[['HP', 'Attack', 'Defense']].head()

dipanjanS

poke_df = pd.read_csv('datasets/Pokemon.csv', encoding='utf-8') 
poke_df.head()

dipanjanS

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import scipy.stats as spstats

%matplotlib inline

dipanjanS

%%time

responses = []
for i in tqdm(range(10000)):
    API_URL = 'http://0.0.0.0:5000/apparel_classifier/api/v1/model2_predict'
    # sending post request and saving response as response object
    r = requests.post(url=API_URL, data=data)
    responses.append(r.json())
len(responses)
print('Inference time per image: {} ms'.format((326 / 10000) * 1000))