This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
guards_advanced = urllib.request.urlopen("https://rotogrinders.com/pages/nba-advanced-player-stats-guards-181885").read() | |
guards_advancedguards_ = bs.BeautifulSoup(guards_advanced, 'lxml') | |
#leaving out a number of lines necessary to extract data, see github repo for full code if you'd like. | |
guards_advanced_col_names = col_names.split() | |
print(guards_advanced_col_names) | |
#could also use pandas read_html method as well | |
guards_advanced_dfs = pd.read_html("https://rotogrinders.com/pages/nba-advanced-player-stats-guards-181885") | |
guards_advanced_stats_df = guards_advanced_dfs[2] | |
guards_advanced_stats_df.tail() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#pipeline adjustment to export data to MongoDB | |
from pymongo import MongoClient | |
from scrapy.conf import settings | |
class MongoDBPipeline(object): | |
def __init__(self): | |
connection = MongoClient( | |
settings['MONGODB_SERVER'], | |
settings['MONGODB_PORT']) | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import scrapy | |
import json | |
import requests | |
import re | |
from time import sleep | |
import sys | |
class LetgoSpider(scrapy.Spider): | |
name = 'letgo' |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import scrapy | |
import sys | |
class CraigslistSpider(scrapy.Spider): | |
name = 'craigslist' | |
allowed_domains = ['asheville.craigslist.org'] | |
start_urls = ['https://asheville.craigslist.org/search/sss'] | |
def parse(self, response): |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#facebook marketplace | |
from selenium import webdriver | |
from time import sleep | |
from selenium.webdriver.common.keys import Keys | |
from selenium.webdriver.support.ui import WebDriverWait | |
from selenium.webdriver.common.by import By | |
from selenium.webdriver.support import expected_conditions as EC | |
from pymongo import MongoClient | |
class App: |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
locations_ten_or_more = all_items_df.groupby(['Location']).filter(lambda g: g.Location.value_counts() >= 10) \ | |
.loc[:,['Location','Description', 'Price', 'Title', 'Url']] | |
#checking the number of locations with less than 10 items | |
len_of_locs = len(locations_ten_or_more.groupby("Location").size()) | |
print(f'There are {len_of_locs} cities with 10 items or more.') | |
print('\n') | |
#checking the locations with the most items in this subset | |
print('Locations with the most amount of items in this subset:') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#execute Summary Extractor model | |
ml = MonkeyLearn('insert api key here') | |
data = list(nlp_df_sample.iloc[:,7]) | |
model_id = 'ex_94WD2XxD' | |
summary_model_results = ml.extractors.extract(model_id, data, production_model=True) | |
print(summary_model_results.body) | |
#execute Price Extractor model | |
data = list(nlp_df_sample.iloc[:,7]) | |
model_id = 'ex_wNDME4vE' |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import scrapy | |
class CraigslistWebscrapingItem(scrapy.Item): | |
name = scrapy.Field() | |
price = scrapy.Field() | |
location = scrapy.Field() | |
date = scrapy.Field() | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# vehicles are skewing boxplot too much; all rows at or above 1.8k appear to be motor vehicles. | |
motor_vehicles = postings.loc[postings.price >= 1800.0, :] | |
motor_vehicles.plot.bar('name', 'price', figsize=(9,9)) | |
plt.ylabel("Price") | |
plt.xlabel("Vehicle") | |
plt.show(); |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#Removing all locations with 2 or less items. | |
counts = non_mv.location.value_counts() | |
loc_gt2 = counts[counts > 2] | |
popular_locations = non_mv[non_mv.location.isin(loc_gt2.keys())] | |
plt.figure(figsize=(10,5)) | |
sns.violinplot(x="location", y="price", data=popular_locations, scale="width", inner="stick") | |
plt.show(); |
OlderNewer