How do I update a defaultdict using a loop? - python

I created a dictionary
TTR_of_speakers = defaultdict(int)
TTR_of_speakers = {}
and I wrote a program that does some computations that results in a value called TTR.
for record in cwrecords:
if record["speaker_name"] == "Joe Biden":
text = record["text"]
processed = nlp(text)
textw = [t.lemma_ for t in processed]
N += len(textw)
total_types |= set(textw)
V = len(total_types)
TTR = float(V)/float(N)
How do I put the TTR value into the dictionary with the key as Joe Biden?

Related

How to add the value from list of tuples

I am extracting from the log file and print using the below code
for line in data:
g = re.findall(r'([\d.]+).*?(GET|POST|PUT|DELETE)', line)
print (g)
[('1.1.1.1', 'PUT')]
[('2.2.2.2', 'GET')]
[('1.1.1.1', 'PUT')]
[('2.2.2.2', 'POST')]
How to add to the output
output
1.1.1.1: PUT = 2
2.2.2.2: GET = 1,POST=1
You could use a dictionary to count:
# initialize the count dict
count_dict= dict()
for line in data:
g = re.findall(r'([\d.]+).*?(GET|POST|PUT|DELETE)', line)
for tup in g:
# get the counts for tuple tup if we don't have it yet
# use 0 (second argument to .get)
num= count_dict.get(tup, 0)
# increase the count and write it back
count_dict[tup]= num+1
# now iterate over the key (tuple) - value (counts)-pairs
# and print the result
for tup, count in count_dict.items():
print(tup, count)
Ok, I have to admit this doesn't give the exact output, you want, but from this you can do in a similar manner:
out_dict= dict()
for (comma_string, request_type), count in count_dict.items():
out_str= out_dict.get(comma_string, '')
sep='' if out_str == '' else ', '
out_str= f'{out_str}{sep}{request_type} = {count}'
out_dict[comma_string]= out_str
for tup, out_str in out_dict.items():
print(tup, out_str)
From your data that outputs:
1.1.1.1 PUT = 2
2.2.2.2 GET = 1, POST = 1
I would look towards Counter.
from collections import Counter
results = []
for line in data:
g = re.findall(r'([\d.]+).*?(GET|POST|PUT|DELETE)', line)
results.append(g[0])
ip_list = set(result[0] for result in results)
for ip in ip_list:
print(ip, Counter(result[1] for result in results if result[0] == ip ))
You can use collection.defaultdict
Ex:
from collections import defaultdict
result = defaultdict(list)
for line in data:
for ip, method in re.findall(r'([\d.]+).*?(GET|POST|PUT|DELETE)', line):
result[ip].append(method)
for k, v in result.items():
temp = ""
for i in set(v):
temp += " {} = {}".format(i, v.count(i))
print("{}{}".format(k, temp))
from collections import Counter
x = [[('1.1.1.1', 'PUT')],[('2.2.2.2', 'GET')],[('1.1.1.1', 'PUT')],[('2.2.2.2', 'POST')]]
# step 1: convert x into a dict.
m = {}
for i in x:
a, b = i[0]
if a not in m.keys():
m[a] = [b]
else:
x = m[a]
x.append(b)
m[a] = x
print('new dict is {}'.format(m))
# step 2 count frequency
m_values = list(m.values())
yy = []
for i in m_values:
x = []
k = list(Counter(i).keys())
v = list(Counter(i).values())
for i in range(len(k)):
x.append(k[i] + '=' + str(v[i]))
yy.append(x)
# step 3, update the value of the dict
m_keys = list(m.keys())
n = len(m_keys)
for i in range(n):
m[m_keys[i]] = yy[i]
print("final dict is{}".format(m))
Output is
new dict is {'1.1.1.1': ['PUT', 'PUT'], '2.2.2.2': ['GET', 'POST']}
final dict is{'1.1.1.1': ['PUT=2'], '2.2.2.2': ['GET=1', 'POST=1']}
Without dependencies and using a dict for counting, in a very basic way. Given the data_set:
data_set = [[('1.1.1.1', 'PUT')],
[('2.2.2.2', 'GET')],
[('2.2.2.2', 'POST')],
[('1.1.1.1', 'PUT')]]
Initialize the variables (manually, just few verbs) then iterate over the data:
counter = {'PUT': 0, 'GET': 0, 'POST': 0, 'DELETE': 0}
res = {}
for data in data_set:
ip, verb = data[0]
if not ip in res:
res[ip] = counter
else:
res[ip][verb] += 1
print(res)
#=> {'1.1.1.1': {'PUT': 1, 'GET': 0, 'POST': 1, 'DELETE': 0}, '2.2.2.2': {'PUT': 1, 'GET': 0, 'POST': 1, 'DELETE': 0}}
It's required to format the output to better fits your needs.

Aggregating values in one column by their corresponding value in another from two files

had a question regarding summing the multiple values of duplicate keys into one key with the aggregate total. For example:
1:5
2:4
3:2
1:4
Very basic but I'm looking for an output that looks like:
1:9
2:4
3:2
In the two files I am using, I am dealing with a list of 51 users(column 1 of user_artists.dat) who have the artistID(column 2) and how many times that user has listened to that particular artist given by the weight(column 3).
I am attempting to aggregate the total times that artist has been played, across all users and display it in a format such as:
Britney Spears (289) 2393140. Any help or input would be so appreciated.
import codecs
#from collections import defaultdict
with codecs.open("artists.dat", encoding = "utf-8") as f:
artists = f.readlines()
with codecs.open("user_artists.dat", encoding = "utf-8") as f:
users = f.readlines()
artist_list = [x.strip().split('\t') for x in artists][1:]
user_stats_list = [x.strip().split('\t') for x in users][1:]
artists = {}
for a in artist_list:
artistID, name = a[0], a[1]
artists[artistID] = name
grouped_user_stats = {}
for u in user_stats_list:
userID, artistID, weight = u
grouped_user_stats[artistID] = grouped_user_stats[artistID].astype(int)
grouped_user_stats[weight] = grouped_user_stats[weight].astype(int)
for artistID, weight in u:
grouped_user_stats.groupby('artistID')['weight'].sum()
print(grouped_user_stats.groupby('artistID')['weight'].sum())
#if userID not in grouped_user_stats:
#grouped_user_stats[userID] = { artistID: {'name': artists[artistID], 'plays': 1} }
#else:
#if artistID not in grouped_user_stats[userID]:
#grouped_user_stats[userID][artistID] = {'name': artists[artistID], 'plays': 1}
#else:
#grouped_user_stats[userID][artistID]['plays'] += 1
#print('this never happens')
#print(grouped_user_stats)
how about:
import codecs
from collections import defaultdict
# read stuff
with codecs.open("artists.dat", encoding = "utf-8") as f:
artists = f.readlines()
with codecs.open("user_artists.dat", encoding = "utf-8") as f:
users = f.readlines()
# transform artist data in a dict with "artist id" as key and "artist name" as value
artist_repo = dict(x.strip().split('\t')[:2] for x in artists[1:])
user_stats_list = [x.strip().split('\t') for x in users][1:]
grouped_user_stats = defaultdict(lambda:0)
for u in user_stats_list:
#userID, artistID, weight = u
grouped_user_stats[u[0]] += int(u[2]) # accumulate weights in a dict with artist id as key and sum of wights as values
# extra: "fancying" the data transforming the keys of the dict in "<artist name> (artist id)" format
grouped_user_stats = dict(("%s (%s)" % (artist_repo.get(k,"Unknown artist"), k), v) for k ,v in grouped_user_stats.iteritems() )
# lastly print it
for k, v in grouped_user_stats.iteritems():
print k,v

How can I optimise in term of time this python code

I write this code but I find it very slow and I don't know how to really improve it in term of time. data is a json object with approximately 70 000 key in it. I think the slowest part is the actors part because i'm iterating on a list (which contain at most 3 elements).
genres_number = {}
actors_number = {}
for movie in data:
for genre in data[movie]["genres"]:
if data[movie]["actors"] != None:
for actor in data[movie]["actors"]:
if actor not in actors_number.keys():
actors_number[actor] = 1
else:
actors_number[actor] = actors_number[actor] + 1
if genre not in genres_number.keys():
genres_number[genre] = 1
else:
genres_number[genre] = genres_number[genre] + 1
res = []
res.append(genres_number)
res.append(actors_number)
return res
How does this work for you
from collections import defaultdict
def get_stats(data):
genres_number = defaultdict(int)
actors_number = defaultdict(int)
for movie in data:
actors = movie.get('actors')
if actors:
for actor in actors:
actors_number[actor] += 1
genres = movie.get('genres')
for genre in genres:
genres_number[actor] += 1
res = []
res.append(dict(genres_number))
res.append(dict(actors_number))
return res

NLTK output changes when using the same input on the same machine

The next piece of code returns different output with the same input(self.SynSets)
Why can it be happening? Am I doing something wrong? or is it caused by python?
def FilterSynSets(self):
self.filteredSysNets = {}
for synset in self.SysNets:
for subsynset in self.SysNets:
length = wn.path_similarity(synset,subsynset)
if not length is None\
and length !=1\
and length >0:
target = synset.__str__().replace("'","")
source =subsynset.__str__().replace("'","")
connection="\"{}\"->\"{}\" [label={}]".format(
target,
source,
str(round(length,3)))
self.filteredSysNets[connection] = length
oldLength = len(self.filteredSysNets)
avarageVal = sum(self.filteredSysNets.values())/len(self.filteredSysNets)
self.filteredSysNets = {k: v for k,v in self.filteredSysNets.items() if v>=avarageVal}
newLength = len(self.filteredSysNets)
prt = newLength/oldLength*100
print ("avr -{}\n old -{}\n new - {}\n prec={}".format(avarageVal,oldLength,newLength,prt))
return self
Outputs:
http://screencast.com/t/eFMOROfkPXR
http://screencast.com/t/Fdd6ufhA

python generating nested dictionary key error

I am trying to create a nested dictionary from a mysql query but I am getting a key error
result = {}
for i, q in enumerate(query):
result['data'][i]['firstName'] = q.first_name
result['data'][i]['lastName'] = q.last_name
result['data'][i]['email'] = q.email
error
KeyError: 'data'
desired result
result = {
'data': {
0: {'firstName': ''...}
1: {'firstName': ''...}
2: {'firstName': ''...}
}
}
You wanted to create a nested dictionary
result = {} will create an assignment for a flat dictionary, whose items can have any values like "string", "int", "list" or "dict"
For this flat assignment
python knows what to do for result["first"]
If you want "first" also to be another dictionary you need to tell Python by an assingment
result['first'] = {}.
otherwise, Python raises "KeyError"
I think you are looking for this :)
>>> from collections import defaultdict
>>> mydict = lambda: defaultdict(mydict)
>>> result = mydict()
>>> result['Python']['rules']['the world'] = "Yes I Agree"
>>> result['Python']['rules']['the world']
'Yes I Agree'
result = {}
result['data'] = {}
for i, q in enumerate(query):
result['data']['i'] = {}
result['data'][i]['firstName'] = q.first_name
result['data'][i]['lastName'] = q.last_name
result['data'][i]['email'] = q.email
Alternatively, you can use you own class which adds the extra dicts automatically
class AutoDict(dict):
def __missing__(self, k):
self[k] = AutoDict()
return self[k]
result = AutoDict()
for i, q in enumerate(query):
result['data'][i]['firstName'] = q.first_name
result['data'][i]['lastName'] = q.last_name
result['data'][i]['email'] = q.email
result['data'] does exist. So you cannot add data to it.
Try this out at the start:
result = {'data': []};
You have to create the key data first:
result = {}
result['data'] = {}
for i, q in enumerate(query):
result['data'][i] = {}
result['data'][i]['firstName'] = q.first_name
result['data'][i]['lastName'] = q.last_name
result['data'][i]['email'] = q.email

Categories