def assign_chk(self, v):
"""
Assign value from menu to global settings.
This is to pass values into the self.set, which
is then saved in settings.py.
I.e.:
self.set.set_recursive = self.var_sett_recursive.get()
"""
setattr(self.set, 'set_%s' % v,
getattr(self, 'var_sett_%s' % v).get())
if v == 'sameinout' and self.set.set_sameinout:
# "Save in same dir" option is on, so set the paths
if self.set.set_dir != self.set.NOP:
self.set.set_dirout = self.set.set_dir
# Same as above, but for a file:
if self.set.set_file != self.set.NOP:
self.set.set_dirout = helpers.get_file_path(self.set.set_file)
self.master.update_gui()
if v == 'sameinout' and not self.set.set_sameinout:
self.set.set_dirout = self.set.NOP
self.master.update_gui()
if v == 'recursive':
self.master.update_gui()
def write_to_file(results):
file_path = helpers.get_file_path('yelp.json', subdirectory='results')
f = open(file_path, 'w')
f.write(json.dumps(results))
# Challenge: Figure out how to print all of the reviews for Tomate on Noyes.
def write_to_file(html):
file_path = helpers.get_file_path('spotify_album_artists.html', subdirectory='results')
f = open(file_path, 'w')
f.write(html)
f.close()
browser= webbrowser.get('chrome')
absolute_path = os.path.abspath(file_path)
browser.open('file://' + absolute_path)
def get_yelp_categories_children(parent):
f = open(helpers.get_file_path('categories.json'), 'rb')
data = json.loads(f.read())
categories = []
for record in data:
if parent in record['parents']:
categories.append(record['title'])
categories.sort()
return categories
def problem_7():
_print_title('Problem 7')
def get_mail_providers(file):
providers = []
for line in file:
line = line.replace('\n', '')
tokens = line.split('@')
if len(tokens) == 1:
continue
providers.append(tokens[-1])
return providers
file_path = helpers.get_file_path('contacts.csv')
f = open(file_path, 'r')
print(get_mail_providers(f))
def save_urls_to_database(urls):
db_path = helpers.get_file_path('test_database.db', subdirectory='results')
create_table_if_does_not_exist(db_path)
delete_all_rows_in_table(db_path, 'Images')
conn = sqlite3.connect(db_path)
cur = conn.cursor()
for url in urls:
print('Writing', url, 'to the database...')
cur.execute(
'''
INSERT INTO Images (url)
VALUES (?)''', (url, ))
cur.close()
conn.commit()
conn.close()
def problem_6():
_print_title('Problem 6')
'''
The errors have been corrected in this code, but the errors are:
file_to_data:
1. incorrect syntax for adding a dictionary to a list. Use append not +=
2. needs to skip the first line (because it's a header row)
3. prints the data list instead of returning it
generate_mailers:
4. The string.format is treating the person object as a list,
but it's a dictionary
'''
def file_to_data(file):
data = []
counter = 0
for line in file:
counter += 1
if counter == 1:
# skips header row:
continue
line = line.replace('\n', '')
cells = line.split(',')
data.append({
'first_name': cells[0],
'last_name': cells[1],
'email': cells[2]
})
return data
def generate_mailers(data):
for person in data:
print('''
To: {0}
Dear {1},
Please send us some money for our important cause.
-- The Nature Conservancy
'''.format(person['email'], person['first_name']))
file_path = helpers.get_file_path('contacts.csv')
file = open(file_path, 'r')
generate_mailers(file_to_data(file))
file.close()
def browse_file(self, *e):
"""
Browse for a file.
"""
filetypes = self.get_file_descriptions()
path = elements.Browse(mode='file',
filetypes=filetypes,
initpath=self.set.set_last_filepath,
lng=self.lng).path
if path != '':
self.set.set_file = path
path_to_file = helpers.get_file_path(self.set.set_file)
self.set.set_last_filepath = path_to_file
self.set.set_dir = self.set.NOP
# If same/in out is selected, set the proper
# out path:
if self.set.set_sameinout:
self.set.set_dirout = path_to_file
self.master.update_gui()
self.master.show_filesdir()
def problem_8():
_print_title('Problem 8')
def get_mail_groups(file):
my_dictionary = {}
for line in file:
line = line.replace('\n', '')
cells = line.split('@')
if len(cells) == 1:
continue
provider = cells[1]
email = line.split(',')[-1]
if my_dictionary.get(provider) is None:
my_dictionary[provider] = []
my_dictionary[provider].append(email)
return my_dictionary
file_path = helpers.get_file_path('contacts.csv')
f = open(file_path, 'r')
print(get_mail_groups(f))
import pandas as pd
import sqlite3
import helpers
# Now let's ask a different question. How many allegations are there
# by Beat?
file_path = helpers.get_file_path('cpd.db', subdirectory='data_sources')
conn = sqlite3.connect(file_path)
df = pd.read_sql_query(
'''
SELECT beat_id, count(beat_id) as num_complaints
FROM data_allegation
GROUP BY beat_id
ORDER BY num_complaints desc;
''', conn)
pd.set_option('display.max_colwidth',
-1) # so the table does not get truncated.
template = '''
<html>
<head>
<title>{header}</title>
<link rel="stylesheet" href="styles.css" />
</head>
<body>
<h1>{header}</h1>
<p>{summary}</p>
{table}
</body>
</html>
'''
import helpers
import pprint
import json
file_path = helpers.get_file_path('artists.json', subdirectory='data_sources')
f = open(file_path, 'r')
artists = json.load(f)
# pprint.pprint(artists)
print(artists)
'''
Challenges:
1. Print the name of the third artist in the list
2. Print the url that is associated with the image for the second artist
3. Build a list of image urls
4. Print the name of all of the artists
'''
from urllib.request import urlopen
import helpers
# From a local file:
file_path = helpers.get_file_path('sample_file.txt', subdirectory='sample_files')
f = open(file_path, 'r')
# output it to the screen:
for line in f:
print(line)
# From a remote file:
results = urlopen('http://www.google.com').read().decode('utf-8', 'ignore')
# 2. print it to the screen
print(results)
import helpers
some_data = [
{
'name': 'Sally',
'age': 34
},
{
'name': 'Larry',
'age': 14
},
{
'name': 'Vivian',
'age': 15
},
{
'name': 'Mari',
'age': 20
},
{
'name': 'Jessie',
'age': 50
},
]
file_path = helpers.get_file_path('names.txt', subdirectory='results')
f = open(file_path, 'w')
for item in some_data:
f.write(item['name'] + '\n')
f.close()
def write_to_file(results):
file_path = helpers.get_file_path('yelp.json', subdirectory='results')
f = open(file_path, 'w')
f.write(json.dumps(results))
f.close()
'header': 'This is my first page title',
'image_url': '../sample_files/kittens.jpg',
'summary': 'This is a very cute photo of a kitten'
}, {
'header': 'This is my second page title',
'image_url': '../sample_files/kittens.jpg',
'summary': 'This is a very cute photo of a kitten'
}, {
'header': 'This is my third page title',
'image_url': '../sample_files/kittens.jpg',
'summary': 'This is a very cute photo of a kitten'
}, {
'header': 'This is my fourth page title',
'image_url': '../sample_files/kittens.jpg',
'summary': 'This is a very cute photo of a kitten'
}, {
'header': 'This is my fifth page title',
'image_url': '../sample_files/kittens.jpg',
'summary': 'This is a very cute photo of a kitten'
}]
# generate an HTML file for each item in the list
counter = 1
for item in data:
html_text = template.format(**item)
file_path = helpers.get_file_path('cat_page_{0}.html'.format(counter),
subdirectory='results')
f = open(file_path, 'w')
f.write(html_text)
f.close()
counter += 1
color='teal',
radius=available_bikes * 8,
fill_color='teal',
fill_opacity=0.6)
marker.add_to(folium_map)
template = '''
<html>
<head>
<title>{header}</title>
<link rel="stylesheet" href="styles.css" />
</head>
<body>
<h1>{header}</h1>
<p>{summary}</p>
<div style="width: 800px; margin:auto;">
{map}
</div>
</body>
</html>
'''
html_text = template.format(
header='My Webpage Title',
summary='Here, we can put a summary of this web page',
map=folium_map._repr_html_())
print('generating the map file...')
file_path = helpers.get_file_path('embedded_map.html', subdirectory='results')
f = open(file_path, 'w')
f.write(html_text)
f.close()
# https://python-visualization.github.io/folium/
# https://blog.prototypr.io/interactive-maps-with-python-part-1-aa1563dbe5a9
# https://nbviewer.jupyter.org/github/vincentropy/python_cartography_tutorial/blob/master/part1_basic_folium_maps.ipynb
import folium
import json
import urllib
import helpers
import pprint
folium_map = folium.Map(
location=[42.004583, -87.661406],
zoom_start=13,
tiles="Stamen watercolor" # Switch to "Stamen toner"
)
print('generating the map file...')
file_name = 'map_no_data.html'
file_path = helpers.get_file_path(file_name, subdirectory='results')
folium_map.save(file_path)
pd.set_option('display.max_colwidth', -1) # so the table does not get truncated.
def display_image_html(entry):
# instead of showing a dictionary, use the 'url' key to display an image:
return '<img src="{0}" />'.format(entry['url'])
def display_genres(entry):
# instead of showing a list, convert to a comma-separated string:
return ', '.join(entry)
def display_link(entry):
# instead of just showing the entry, convert the entry to a link:
return '<a href="{0}">View on Spotify</a>'.format(entry)
file_path = helpers.get_file_path('artists.json', subdirectory='data_sources')
dataframe = pd.read_json(file_path)
# how we want each column to be displayed (see documentation):
# http://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.to_html.html
formatters = {
'image': display_image_html,
'genres': display_genres,
'url': display_link
}
template = '''
<html>
<head>
<title>{header}</title>
<link rel="stylesheet" href="styles.css" />
import helpers
template = '''
<html>
<head><title>{header}</title></head>
<body>
<h1>{header}</h1>
<p>{summary}</p>
<img src="{image_url}" />
</body>
</html>
'''
html_text = template.format(header='This is my page title',
image_url='../sample_files/kittens.jpg',
summary='This is a very cute photo of a kitten')
file_path = helpers.get_file_path('cat_page.html', subdirectory='results')
f = open(file_path, 'w')
f.write(html_text)
f.close()
from urllib.request import urlopen
import helpers
# 1. get it from the internet
results = urlopen('http://www.google.com').read().decode('utf-8', 'ignore')
# 2. print it to the screen
print(results)
# 3. write it to a file
# create a file path that will write to results/google.html:
file_path = helpers.get_file_path('google.html', subdirectory='results')
f = open(file_path, 'w')
f.write(results)
f.close()
def write_to_file(results, file_name='yelp_data.json'):
file_path = helpers.get_file_path(file_name, subdirectory='results')
f = open(file_path, 'w')
f.write(json.dumps(results))
f.close()
"genres": ["dance pop", "pop"],
"id": "1HY2Jd0NmPuamShAr6KMms",
"image": {
"height": 640,
"url":
"https://i.scdn.co/image/6fdeaf010a560e24ed9fdfab939dd0ab01d3d32c",
"width": 640
},
"url": "https://api.spotify.com/v1/artists/1HY2Jd0NmPuamShAr6KMms"
}
template = '''
<html>
<head><title>{artist}</title></head>
<body>
<h1>{artist}</h1>
<p>Genres: {genres}</p>
<img src="{image_url}" />
</body>
</html>
'''
# Currently the template is being populated with the wrong
# data. Fix it so that it uses the data from artists:
html_text = template.format(artist='a', genres='b', image_url='c')
# write to file:
file_path = helpers.get_file_path('lady_gaga.html', subdirectory='results')
f = open(file_path, 'w')
f.write(html_text)
f.close()
import helpers
'''
Problem 8
Write a function called get_students_by_major that takes
a file object as an argument and returns a
list of student names that where they key is the major
and the value is a list of students belonging to the major.
'''
def get_students_by_major(file, student_major):
student_names = []
for line in file.readlines()[1:]:
line = line.replace('\n', '')
cells = line.split(',')
major = cells[2]
if student_major == major:
full_name = cells[0] + ' ' + cells[1]
student_names.append(full_name)
return student_names
f = open(helpers.get_file_path('students.csv'), 'r')
student_names = get_students_by_major(f, 'Psychology')
print(student_names)
import pylab
import matplotlib.pyplot as plt
import numpy as np
import sqlite3
import helpers
# get data:
file_path = helpers.get_file_path('cpd.db', subdirectory='data_sources')
conn = sqlite3.connect(file_path)
cur = conn.cursor()
cur.execute('''
SELECT beat_id, count(beat_id) as num_complaints
FROM data_allegation
GROUP BY beat_id
ORDER BY num_complaints
LIMIT 25;
''')
results = cur.fetchall()
cur.close()
conn.close()
# make a list with all of the beat names
# and a list with all of the complaint counts
beats = []
counts = []
for result in results:
# omit empty data:
if result[0] is None or result[1] is None:
continue
beats.append('Beat ' + str(int(result[0])))
counts.append(result[1])
import pylab
import matplotlib.pyplot as plt
import numpy as np
import sqlite3
import helpers
# How do we display the same query as a bar chart?
# Answer: use pylab and matplotlib
file_path = helpers.get_file_path('cpd.db', subdirectory='data_sources')
conn = sqlite3.connect(file_path)
cur = conn.cursor()
cur.execute('''
SELECT beat_id, count(beat_id) as num_complaints
FROM data_allegation
GROUP BY beat_id
ORDER BY num_complaints
LIMIT 25;
''')
results = cur.fetchall()
cur.close()
conn.close()
# make a list with all of the beat names
# and a list with all of the complaint counts
beats = []
counts = []
for result in results:
# omit empty data:
if result[0] is None or result[1] is None:
continue
beats.append('Beat ' + str(int(result[0])))
font-family: Arial;
margin: 30px 100px 30px 100px;
}}
table {{ margin-top: 20px;}}
</style>
</head>
<body>
<h1>{artist_name}</h1>
<p>More info <a href="{share_url}">here...</a></p>
<img src="{image_url}" />
{tracks_table}
</body>
</html>
'''
artist_data = spotify.get_artists('beyonce')
artist = artist_data[0]
tracks_data = spotify.get_tracks_by_artist(artist['id'])
tracks_table = spotify.get_formatted_tracklist_table_html(tracks_data)
# print(artist)
# print(tracks_data)
html_text = template.format(artist_name=artist['name'],
image_url=artist['image_url_small'],
share_url='share_url',
tracks_table=tracks_table)
file_path = helpers.get_file_path('beyonce.html', subdirectory='results')
f = open(file_path, 'w')
f.write(html_text)
f.close()
# inject results into simple HTML page:
template = '''
<html>
<head>
<title>Northwestern Search Results</title>
</head>
<body>
<h1>Search Results</h1>
{body}
</body>
</html>
'''.format(body=body_section)
# write everything to a file:
file_path = helpers.get_file_path(search_term.replace(' ', '_') + '.html',
subdirectory='results')
absolute_path = os.path.abspath(file_path)
f = open(file_path, 'w')
f.write(template)
f.close()
print('Copy this link into your web browser to see the results:')
print('file://' + absolute_path)
try:
# open web browser with the results:
browser = webbrowser.get('chrome')
browser.open('file://' + absolute_path)
except:
print('Your web page did not open automatically.')
def write_to_file(data):
file_path = helpers.get_file_path('spotify_artists.json', subdirectory='results')
f = open(file_path, 'w')
f.write(json.dumps(data))
import sqlite3
import helpers
conn = sqlite3.connect(helpers.get_file_path('../databases/flights.db'))
cur = conn.cursor()
# list columns for each of the available tables:
for table in ['airports', 'airlines', 'routes']:
cur.execute("pragma table_info({0});".format(table))
results = cur.fetchall()
# add a little formatting to make things easier to read:
print('\n')
print(table)
print('-' * 35)
for row in results:
print(row[1] + ' (' + row[2] + ')')
cur.close()
conn.close()
import helpers
template = '''
<html>
<head><title>{header}</title></head>
<body>
<h1>{header}</h1>
<p>{summary}</p>
<img src="{image_url}" />
</body>
</html>
'''
html_text = template.format(
header='This is my page title',
image_url='../sample_files/kittens.jpg',
summary='This is a very cute photo of a kitten'
)
file_path = helpers.get_file_path('cat_page.html')
f = open(file_path, 'w')
f.write(html_text)
f.close()
