t = Table(rows=[
[uid(), "broccoli", "vegetable"],
[uid(), "turnip", "vegetable"],
[uid(), "asparagus", "vegetable"],
[uid(), "banana", "fruit" ],
])
print t.rows[0] # A list of rows.
print t.columns[1] # A list of columns, where each column is a list of values.
print
# Columns can be manipulated directly like any other Python list.
# This can be slow for large tables. If you need a fast way to do matrix math,
# use numpy (http://numpy.scipy.org/) instead.
# The purpose of Table is data storage.
t.columns.append([
"green",
"purple",
"white",
"yellow"
])
# Save as a comma-separated (unicode) text file.
t.save("food.txt")
# Load a table from file.
t = Table.load("food.txt")
pprint(t, truncate=50, padding=" ", fill=".")
import os, sys
sys.path.append(os.path.join("..", "..", ".."))
from pattern.web import Twitter, hashtags
from pattern.table import Table, pprint
# This example retrieves tweets containing given keywords from Twitter (http://twitter.com).
try:
# We store tweets in a Table that can be saved as a text file.
# In the first column, we'll store a unique ID for each tweet.
# We only want to add the latest tweets, i.e. those we haven't previously encountered.
# With an index() on the first column we can quickly check if an ID already exists.
# The index becomes important once more and more rows are added to the table (speed).
table = Table.load("cool.txt")
index = table.index(table.columns[0])
except:
table = Table()
index = {}
engine = Twitter()
# With cached=False, a live request is sent to Twitter,
# so we get the latest results for the query instead of those in the local cache.
for tweet in engine.search("is cooler than", count=25, cached=False):
print tweet.description
print tweet.author
print tweet.date
print hashtags(tweet.description) # Keywords in tweets start with a #.
print
# Create a unique ID based on the tweet content and author.
import os, sys
sys.path.append(os.path.join("..", "..", ".."))
from pattern.web import Twitter, hashtags
from pattern.table import Table, pprint
# This example retrieves tweets containing given keywords from Twitter (http://twitter.com).
try:
# We store tweets in a Table that can be saved as a text file.
# In the first column, we'll store a unique ID for each tweet.
# We only want to add the latest tweets, i.e. those we haven't previously encountered.
# With an index() on the first column we can quickly check if an ID already exists.
# The index becomes important once more and more rows are added to the table (speed).
table = Table.load("cool.txt")
index = table.index(table.columns[0])
except:
table = Table()
index = {}
engine = Twitter()
# With cached=False, a live request is sent to Twitter,
# so we get the latest results for the query instead of those in the local cache.
for tweet in engine.search("is cooler than", count=25, cached=False):
print tweet.description
print tweet.author
print tweet.date
print hashtags(tweet.description) # Keywords in tweets start with a #.
print
# It can be saved as a CSV text file that is both human/machine readable.
# See also: examples/01-web/03-twitter.py
# Supported values that are imported and exported correctly:
# str, unicode, int, float, bool, None
# For other data types, custom encoder and decoder functions can be used.
t = Table(rows=[
[uid(), "broccoli", "vegetable"],
[uid(), "turnip", "vegetable"],
[uid(), "asparagus", "vegetable"],
[uid(), "banana", "fruit"],
])
print t.rows[0] # A list of rows.
print t.columns[1] # A list of columns, where each column is a list of values.
print
# Columns can be manipulated directly like any other Python list.
# This can be slow for large tables. If you need a fast way to do matrix math,
# use numpy (http://numpy.scipy.org/) instead.
# The purpose of Table is data storage.
t.columns.append(["green", "purple", "white", "yellow"])
# Save as a comma-separated (unicode) text file.
t.save("food.txt")
# Load a table from file.
t = Table.load("food.txt")
pprint(t, truncate=50, padding=" ", fill=".")
