jiobu1

# Nearest Neighbor

import numpy as np
from sklearn.neighbors import NearestNeighbors
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline

# Select columns that will be used to calculate nearest neighbors
# Added data points
# new = [Transit Score, Bike Score, Total_Schools, Private, Public district, Public Charter, 

jiobu1

def run_prophet(series):
  model = Prophet(daily_seasonality=False,
                  weekly_seasonality=False,
                  yearly_seasonality=False)
  model.fit(series)
  forecast = model.make_future_dataframe(periods=10, freq='Y')
  forecast = model.predict(forecast)
  forecast = forecast[['ds', 'yhat', 'yhat_lower', 'yhat_upper']]
  forecast['City,State'] = series['City,State'].iloc[0]
  forecast = forecast[['City,State','ds', 'yhat', 'yhat_lower', 'yhat_upper']]

jiobu1

# Create list of cities
cities_list = list(population['City,State'])

# group cities from the population_melt.csv
def rnd_series(city):
    subset = population_melt[population_melt['City,State']== city]
    dates = (pd.DataFrame({'ds': pd.to_datetime(population_melt['ds'])}))
    return subset

# create dictionary of city name and grouped population_melt.csv

jiobu1

population_melt = (population.melt(id_vars=['City,State'],
                                   var_name = 'ds',
                                   value_name = 'y'
                                  ).reset_index(drop=True)
                  )

jiobu1

class SchoolData(BaseModel):
    total_schools: int
    percent_high_performing_schools: float
    percent_private: float
    percent_public: float
    percent_charter: float


async def get_school_summary(city: City):
    """Retrieve recommended cities for target city

jiobu1

# Schools Listing Endpoint

async def schools_listings(current_city:City, school_category):
    """
    Listing of school information for the city 
    (locates specific pickled dictionary based on school category for the city)
    - Ratings -> sorted, listed from highest to lowest
    - Type -> public, private, charter
    - Grades -> pre-k, elementary, middle, high school
    - District -> district in city

jiobu1

table = soup.find("table", { "class" : "" })
for row in table.find_all("tr"):
    cell = row.find_all("td")
    if len(cell) == 7:
        school = row.find('a', {'class':'name'}).text.strip()
        try:
            score = row.find('div', {'class': 'circle-rating--small'}).text.strip()
        except AttributeError:
            score = '0/10'
        rating = row.find('div', {'class': 'scale'}).text.strip()

jiobu1

for i in cities['city']:
  fetching = True

  page = 0

  while fetching:  
        page += 1
        url = url_pre +  urllib.parse.quote(i) + '/schools/?page={}&tableView=Overview&view=table'.format(page)       
        print("Fetching ", url)

jiobu1

# Looping through each city in the file
cities = pd.read_csv('csv/cities.csv')

records = []

# selenium driver
driver = webdriver.Chrome()

# url for greatschools pre_url and post_url (with state/city inbetween)
url_pre = 'http://www.greatschools.org/'

jiobu1

from state_abbr import us_state_abbrev as abbr

# create city state list
cities = pd.read_excel('notebooks/datasets/data/schools/csv/List of Cities.xlsx')

# just get the second and third colun
cities = cities[['Unnamed: 1','Unnamed: 2']]

# create new dictionary with reversed key, value pairs
full = dict(map(reversed, abbr.items()))