hamletbatista

## visualize_final_reframe.py
data = []
ages = ["Pre-K", "Grade School", "Teens", "Young Adults", "Over 30", "Seniors"]

top_5 = []
for i in range(5):
    scores = []
    for age in ages:
        scores.append(tuple(rides.sort_values(age, ascending=False)[[age, "Ride"]].iloc[i].values))
    top_5.append(scores)

## get_disney_ride_ratings.py
# Get Disney Attractiveness Ratings
import requests
from bs4 import BeautifulSoup

r = requests.get("https://touringplans.com/disneyland/attractions")
soup = BeautifulSoup(r.text)

rows = []
table = soup.find("table")
for idx, tr in enumerate(table.findAll("tr")):

## enjoyment_score.py
# Data taken from here: https://touringplans.com/disneyland/attractions
# Ties in attraction ratings were resolved by selecting the age group closest to the next-highest score

df['Age Group'] = ["Pre-K", "Grade School", "Seniors",
                   "Pre-K", "Seniors", "Seniors",
                   "Pre-K", "Grade School", "Over 30",
                   "Seniors", "Pre-K", "Pre-K",
                   "Teens", "Teens", "Seniors",
                   "Young Adults", "Young Adults", "Teens",
                   "Pre-K", "Pre-K"]

## visualize_ridetimes.py
#!pip install plotly-express

import pandas as pd
from urllib.parse import urlparse
from collections import Counter
import plotly.express as px
import plotly
import plotly.graph_objects as go

fig = px.scatter(df, x="Average Wait Time", y="Ride Duration", color="Ride", symbol="Ride", height=900, width=1200)

## avgwaittimeandduration.py
average_wait=pd.Series(df.mean(), name="Average Wait Time")
print(average_wait)

#example output
#Astro Orbitor                                     12.453125
#Buzz Lightyear Astro Blasters                     17.953125

duration = pd.Series(ride_durations, name="Ride Duration")
print(duration)

## ridewaittimesjs2py.py
from jinja2 import Template

js_template="""
function drawChart137() {

  var columns = {{columns}};
  var title = "{{title}}";

  return [title, columns];
}

## ridewaittimes.py
script_sel="#new_gchart_slideshow > div.forecast-viewport > ul > li > script"

all_rides = r.html.find(script_sel)

def extract_dates(data):
  start_row = "dateData.addRows\("
  end_row = "\);"

  columns = []
  title = None

## ridesduration.py
r = session.get('https://touringplans.com/disneyland/attractions/duration')

ride_durations = dict()

for tr in r.html.find("#center > table > tr"): #element selected copied from Chrome Developer Tools

  ride = tr.find("td:nth-child(1)")[0].text
  duration = tr.find("td:nth-child(2)")[0].text

  print(ride, duration)

## caption_all_images.py
captions = dict()

for image_url in unique_images:

  try:

    caption = generate_caption(image_url)

    captions[image_url] = caption


## clean_image_urls_part1.py
import re

i = len(df["Custom Extraction 1"])#.split('<img src="')

images = list()

for i, image_list in enumerate(df["Custom Extraction 1"]):
  #print(i)

  images.extend(df["Custom Extraction 1"][i].split('<img src="'))