surging | service engine that provides a lightweight

df = pd.read_csv("https://gist.githubusercontent.com/jerry-shad/7eb2dd4ac75034fcb50ff5549f2e5e21/raw/477c07446a8715f043c9b1ba703a03b2f913bdbf/covid_tsdf.csv")
df.drop(['Unnamed: 0', 'fips', 'non-fed-slaughter', 'fed-slaughter', 'total-slaughter', 'mcd-asl'], axis=1, inplace=True)
for ct in df['county_state'].unique():
    dd = df[df['county_state'] == ct].groupby(['county_state', 'date', 'est'])[['cases','new_cases']].sum().unstack().reset_index()
    dd.columns= ['county_state','date', 'cases', 'new_cases']
    dd['date'] = pd.to_datetime(dd['date'])
    dd['rol7'] = dd[['date','new_cases']].rolling(7).mean()
    fig = plt.figure(figsize=(8,6),dpi=144)
    ax = fig.add_subplot(111)
    colors = sns.color_palette()
    ax2 = ax.twinx()
    ax = sns.lineplot('date', 'rol7', data=dd, color=colors[1], ax=ax)
    ax2 = sns.lineplot('date', 'cases', data=dd, color=colors[0], ax=ax2)
    ax.set_xlim(dd.date.min(), dd.date.max())
    fig.legend(['rolling7','cases'],loc="upper left", bbox_to_anchor=(0.01, 0.95), bbox_transform=ax.transAxes)
    ax.grid(axis='both', lw=0.5)
    locator = mdates.AutoDateLocator()
    ax.xaxis.set_major_locator(locator)
    fig.autofmt_xdate(rotation=45)
    ax.set(title=f'US covid tracking in meat processing plants by county - Linear scale')
    plt.show()

import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import seaborn as sns
from datetime import timedelta, datetime

df = pd.read_csv("https://gist.githubusercontent.com/jerry-shad/7eb2dd4ac75034fcb50ff5549f2e5e21/raw/477c07446a8715f043c9b1ba703a03b2f913bdbf/covid_tsdf.csv")
df.drop(['Unnamed: 0', 'fips', 'non-fed-slaughter', 'fed-slaughter', 'total-slaughter', 'mcd-asl'], axis=1, inplace=True)
for ct in df['county_state'].unique():
    dd = df.groupby([ct, 'date', 'est'])['num-emp'].sum().unstack().reset_index()
    p = sns.lineplot('date', 'values', data=dd, hue='packer', markers=markers, style='cats', ax=axes[j, 0])
    p.set_xlim(data.date.min() - timedelta(days=60), data.date.max() + timedelta(days=60))
    plt.legend(bbox_to_anchor=(1.04, 0.5), loc="center left", borderaxespad=0)

df = pd.read_csv("https://gist.githubusercontent.com/jerry-shad/7eb2dd4ac75034fcb50ff5549f2e5e21/raw/477c07446a8715f043c9b1ba703a03b2f913bdbf/covid_tsdf.csv")
ds_states = df.groupby('county_state').sum().rename({'county_state': 'location'})
ds_states['mortality'] = ds_states['deaths'] / ds_states['popestimate2019'] * 1_000_000
ds_states['daily_mortality'] = ds_states['new_deaths'] / ds_states['popestimate2019'] * 1_000_000
ds_states['daily_mortality7'] = ds_states['daily_mortality'].rolling({'time': 7}).mean()

def subplots(*args, tick_right=True, **kwargs):
    f, ax = plt.subplots(*args, **kwargs)

    if tick_right:
        ax.yaxis.tick_right()
        ax.yaxis.set_label_position("right")
    ax.yaxis.grid(color="lightgrey", linewidth=0.5)
    ax.xaxis.grid(color="lightgrey", linewidth=0.5)
    ax.xaxis.set_tick_params(labelsize=14)
    return f, ax

 _, ax1 = subplots(subplot_kw={'xlim': XLIM})
ax1.set(title=f'US covid tracking in meat processing plants by county - Linear scale')
ax2 = ax1.twinx()

import requests
import json
url = ('http://newsapi.org/v2/top-headlines?'
       'country=us&'
       'apiKey=608bf565c67f4d99994c08d74db82f54')
response = requests.get(url)
di=response.json()
di = json.dumps(di)
for di['articles'] in di:
  print(article['title']) 

{'status': 'ok', 
 'totalResults': 38, 
 'articles': [
              {'source': 
                {'id': 'the-washington-post', 
                 'name': 'The Washington Post'}, 
               'author': 'Derek Hawkins, Marisa Iati', 
               'title': 'Coronavirus updates: Texas, Florida and Arizona officials say early reopenings fueled an explosion of cases - The Washington Post', 
               'description': 'Local officials in states with surging coronavirus cases issued dire warnings Sunday about the spread of infections, saying the virus was rapidly outpacing containment efforts.', 
               'url': 'https://www.washingtonpost.com/nation/2020/07/05/coronavirus-update-us/', 
               'urlToImage': 'https://www.washingtonpost.com/wp-apps/imrs.php?src=https://arc-anglerfish-washpost-prod-washpost.s3.amazonaws.com/public/K3UMAKF6OMI6VF6BNTYRN77CNQ.jpg&w=1440', 
               'publishedAt': '2020-07-05T18:32:44Z', 
               'content': 'Here are some significant developments:\r\n
 

  
The rolling seven-day average for daily new cases in the United States reached a record high for the 27th day in a row, climbing to 48,606 on Sunday, … [+5333 chars]'}])

 

"Iconic powerful bass resonance of Bluedio: 57mm ultra-large dynamic drivers, turbine style housing, with the iconic Bluedio surging low-frequency shock, let you feel the bass resonate deep in the chest, enjoying the best sound quality. Clear and transparent bass, mids and treble, fully exposed to all the details of song, you can hear what the artists really want you to hear, Coldplay or Linkin Park concert played in your ear
"

html=html.replace(/<\w+>/,'').replace(/<\/\w+>/,'').trim();

"Iconic powerful bass resonance of Bluedio: 57mm ultra-large dynamic drivers, turbine style housing, with the iconic Bluedio surging low-frequency shock, let you feel the bass resonate deep in the chest, enjoying the best sound quality. Clear and transparent bass, mids and treble, fully exposed to all the details of song, you can hear what the artists really want you to hear, Coldplay or Linkin Park concert played in your ear
"

import nltk
from nltk.corpus import stopwords
import string

with open('moby.txt', 'r') as f:
    moby_raw = f.read()
    stop = set(stopwords.words('english'))
    moby_tokens = nltk.word_tokenize(moby_raw)
    text_no_stop_words_punct = [t for t in moby_tokens if t not in stop or t not in string.punctuation]

    print(text_no_stop_words_punct)

[...';', 'surging', 'from', 'side', 'to', 'side', ';', 'spasmodically', 'dilating', 'and', 'contracting',...]