rwilleynyc

def plot_pdp(model, X, feature, target=False, return_pd=False, y_pct=True, figsize=(10,9), norm_hist=True, dec=.5):
    # Get partial dependence
    pardep = partial_dependence(model, X, [feature])
    
    # Get min & max values
    xmin = pardep[1][0].min()
    xmax = pardep[1][0].max()
    ymin = pardep[0][0].min()
    ymax = pardep[0][0].max()
    

rwilleynyc

rwilleynyc

name,categories,rating,price
Tacuba,"[{'alias': 'mexican', 'title': 'Mexican'}, {'alias': 'tapas', 'title': 'Tapas Bars'}, {'alias': 'latin', 'title': 'Latin American'}]",3.5,$$
Mi Espiguita Taqueria,"[{'alias': 'mexican', 'title': 'Mexican'}]",4.5,$
El Mero Mero,"[{'alias': 'mexican', 'title': 'Mexican'}]",4.5,$$
Hoja Santa,"[{'alias': 'newmexican', 'title': 'New Mexican Cuisine'}, {'alias': 'mexican', 'title': 'Mexican'}]",4.5,
The Calaveras,"[{'alias': 'bars', 'title': 'Bars'}, {'alias': 'mexican', 'title': 'Mexican'}, {'alias': 'tapasmallplates', 'title': 'Tapas/Small Plates'}]",4.5,$$
Athens Grill & Sports Bar,"[{'alias': 'mexican', 'title': 'Mexican'}]",4,$
Mezquite Restaurant,"[{'alias': 'mexican', 'title': 'Mexican'}, {'alias': 'peruvian', 'title': 'Peruvian'}, {'alias': 'seafood', 'title': 'Seafood'}]",4,$$
Fresco's Cantina,"[{'alias': 'mexican', 'title': 'Mexican'}, {'alias': 'latin', 'title': 'Latin American'}, {'alias': 'newmexican', 'title': 'New Mexican Cuisine'}]",4.5,$$
Chela & Garnacha,"[{'al

rwilleynyc

,id,alias,name,image_url,is_closed,url,review_count,categories,rating,coordinates,transactions,price,location,phone,display_phone,distance
0,EHUNrnIgnhwTnpOm3gEESg,tacuba-astoria,Tacuba,https://s3-media4.fl.yelpcdn.com/bphoto/Q6jPz4xg6QPh4NElULobrA/o.jpg,False,https://www.yelp.com/biz/tacuba-astoria?adjust_creative=TKz2edtltxgYtPzgSrH9EQ&utm_campaign=yelp_api_v3&utm_medium=api_v3_business_search&utm_source=TKz2edtltxgYtPzgSrH9EQ,645,"[{'alias': 'mexican', 'title': 'Mexican'}, {'alias': 'tapas', 'title': 'Tapas Bars'}, {'alias': 'latin', 'title': 'Latin American'}]",3.5,"{'latitude': 40.75585, 'longitude': -73.92447}","['delivery', 'pickup']",$$,"{'address1': '35-01 36th St', 'address2': '', 'address3': '', 'city': 'Astoria', 'zip_code': '11106', 'country': 'US', 'state': 'NY', 'display_address': ['35-01 36th St', 'Astoria, NY 11106']}",+17187862727,(718) 786-2727,1229.3517053099579
1,yvva7IYpD6J7OfKlCdQrkw,mi-espiguita-taqueria-astoria,Mi Espiguita Taqueria,https://s3-media2.fl.yelpcdn.com/bphoto/TEho39G01VJX

rwilleynyc

# Create nested dictionaries to map grades to year and neighbor states
neighbor_grades = {}

for year in df.Year.unique():
    neighbor_grades[year] = {}
    
    for state in df.State.unique():
        # Default score is state score if no neighboring state (i.e. Alaska)
        default_score = df[(df.State==state) & (df.Year==year)]['State Grade'].values[0]
        scores = []

rwilleynyc

import urllib.request
url = 'https://github.com/ritvikmath/StarbucksStoreScraping/raw/master/us_states.geojson'

urllib.request.urlretrieve(url, 'international_data/us_states.geojson')

#manipulate complex shapes
from shapely.geometry import Polygon, MultiPolygon

#manipulate json objects
import json

rwilleynyc

import scipy.stats

# Get unique list of regions
regions = df['Region'].unique()

# For each region, compare quantities of the region against rest of world
for region in regions:
    test = df['Quantity'].loc[(df['Region'] == region)]
    control = df['Quantity'].loc[(df['Region'] != region)]
    results = stats.ttest_ind(test, control)

rwilleynyc

rwilleynyc

import statsmodels.api as sm
from statsmodels.formula.api import ols

# Define target & independent variables
# C(var_name) indicates variable is categorical
formula = 'Quantity ~ Discount + C(Employee) + C(Region) + C(CategoryName)'

# Fit ordinary least squares model to data
lm = ols(formula, df).fit()

rwilleynyc