In [251]:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from wordcloud import WordCloud
import seaborn as sns
import re
from sklearn.feature_extraction import DictVectorizer
sns.set(color_codes=True)
%pylab inline
In [191]:
PATH_TO_FOLDER = "../Yelp/Data/"
BUSINESS = "part_businesses.csv"
TIPS = "part_tips.csv"
USERS = "part_users.csv"
REVIEWS = "part_reviews.csv"
In [192]:
reviews_df = pd.read_csv(PATH_TO_FOLDER+REVIEWS)
business_df = pd.read_csv(PATH_TO_FOLDER+BUSINESS)
tips_df = pd.read_csv(PATH_TO_FOLDER+TIPS)
tips_df = tips_df[["business_id", "date", "likes", "user_id"]] # Удаляем текст
business_df = business_df[["business_id", "city"]]
business_df.columns = ["business_id", "business_city"]
In [193]:
tips_df.head(1)
Out[193]:
In [194]:
reviews_df.head(1)
Out[194]:
Посмотрим, как распределены оценки за ревью
In [195]:
figure(3, figsize=(6,6))
stars_count = reviews_df.groupby("stars")["stars"].count()
labels = ["1", "2", "3", "4", "5"]
explode=(0.03, 0.03, 0.03, 0.03, 0.03)
pie(start_count, labels=labels, shadow=True, startangle=90, explode=explode)
plt.title('Stars of Reviews', bbox={'facecolor':'0.9', 'pad':5})
plt.show()
Видно, что количество положительных оценок превосходит количество отрицательных
In [ ]:
Посчитаем количество слов. Построим график, который покажет, как оценка за рецензию зависит от количества слов в рецензии.
In [173]:
def get_count_of_words(text):
return text.count(' ')+1
reviews_df["count_of_words"] = reviews_df.text.map(lambda s: get_count_of_words(s))
In [174]:
a = reviews_df.groupby(["stars", "count_of_words"]).count_of_words.count()
step = reviews_df["count_of_words"].max()
pd.DataFrame(a).plot(kind='barh')
frame = pylab.gca()
pylab.title("STARS | Count of words")
pylab.xlabel("Count of words")
pylab.ylabel("Stars")
frame.axes.get_yaxis().set_ticks([])
frame.legend_.remove()
plt.yticks([step*(i+1)/2 for i in range(5)], ["1","2","3","4","5"], rotation='horizontal');
plt.show()
На это графике видно, что если человее написал в своем обзоре больше 150 слов, то он, однозначно, получит положительную за нее оценку.
In [ ]:
Считаем ревью людей по городам
In [196]:
reviews_df = reviews_df.merge(business_df, on='business_id', left_index=True, right_index=False)
In [197]:
# Сколько раз для какого города пользователи делали обзоры
business_city_count = pd.DataFrame(reviews_df.groupby(["user_id", "business_city"])["business_city"].count())
business_city_count.columns = ["reviews_for_city"]
business_city_count.reset_index(inplace=True)
In [198]:
# Общее количество ревью для каждого пользователя
review_count = pd.DataFrame(reviews_df.groupby("user_id")["user_id"].count())
review_count.columns = ["reviews_count"]
review_count.reset_index(inplace=True)
Построим гистограмму людей по количеству людей по ревью
In [199]:
review_count_array = review_count["reviews_count"].as_matrix()
max_ = max(review_count_array)
print max_
plt.figure(figsize=(8,8))
plt.hist(review_count_array, bins=max_)
plt.yscale('log')
plt.xticks([i for i in range(max_+1)])
plt.title('Review for person')
plt.xlabel('Count of review')
plt.ylabel('Count of people')
review_count_array = 0
In [200]:
user_city_df = review_count.merge(business_city_count, on='user_id', left_index=True, right_index=False)
In [201]:
user_city_df.head(1)
Out[201]:
In [202]:
def is_only_one_city(count1, count2):
return 1 if (count1==count2) else 0
user_city_df["is_only_one_city"] = user_city_df.apply(lambda s: is_only_one_city(s["reviews_count"], s["reviews_for_city"]), axis=1)
Сколько людей писали review только в одном городе, а сколько в нескольких
In [203]:
figure(3, figsize=(6,6))
count_of_users = user_city_df[["user_id", "is_only_one_city"]]
count_of_users = count_of_users.drop_duplicates()
count_uniq = count_of_users["is_only_one_city"].value_counts()
labels = ["Only one city", "Several cities"]
explode=(0.05, 0)
pie(count_uniq, labels=labels, shadow=True, startangle=90, explode=explode)
plt.title('How many cities was reviewed', bbox={'facecolor':'0.9', 'pad':5})
plt.show()
count_of_users = 0
Сделаем тоже самое для TIPS
In [204]:
tips_city_df = tips_df.merge(business_df, on='business_id', left_index=True, right_index=False)
In [212]:
# Сколько раз для какого города пользователи делали tips
tips_city_count = pd.DataFrame(tips_city_df.groupby(["user_id", "business_city"])["business_city"].count())
tips_city_count.columns = ["tips_for_city"]
tips_city_count.reset_index(inplace=True)
In [214]:
# Общее количество tips для каждого пользователя
tips_count = pd.DataFrame(tips_city_df.groupby("user_id")["user_id"].count())
tips_count.columns = ["tips_count"]
tips_count.reset_index(inplace=True)
In [216]:
tips_city_df = tips_city_count.merge(tips_count, on='user_id', left_index=True, right_index=False)
In [218]:
def is_only_one_city(count1, count2):
return 1 if (count1==count2) else 0
tips_city_df["is_only_one_city"] = tips_city_df.apply(lambda s: is_only_one_city(s["tips_for_city"], s["tips_count"]), axis=1)
tips_city_df.head()
Out[218]:
In [224]:
tips_count_array = tips_city_df["tips_count"].as_matrix()
max_ = max(tips_count_array)
print max_
plt.figure(figsize=(8,8))
plt.hist(tips_count_array, bins=max_)
plt.yscale('log')
plt.xticks([i for i in range(max_+1)])
plt.title('Review for person')
plt.xlabel('Count of review')
plt.ylabel('Count of people')
review_count_array = 0
In [222]:
figure(3, figsize=(6,6))
count_of_users = tips_city_df[["user_id", "is_only_one_city"]]
count_of_users = count_of_users.drop_duplicates()
count_uniq = count_of_users["is_only_one_city"].value_counts()
labels = ["Only one city", "Several cities"]
explode=(0.05, 0)
pie(count_uniq, labels=labels, shadow=True, startangle=90, explode=explode)
plt.title('How many cities was tipped', bbox={'facecolor':'0.9', 'pad':5})
plt.show()
count_of_users = 0
Построим облако тегов для Tips и Reviews
In [305]:
def get_words(text):
"""returns list of words"""
text = re.sub(r"_+", '', text) # Удаляем __, они, почему-то, входят в \w
text = re.sub("\w*\d\w*", "", text) # Удаляем все цифры и слова с цифрами
array = re.findall(r'[\w]+', text) # Выделяем слова
return array
def get_tokens(words):
"""returns list of tokens"""
stop_words = stopwords.words('english')
wordnet_lemmatizer = WordNetLemmatizer()
lems = []
for w in words:
w = w.lower()
if w not in stop_words:
w = wordnet_lemmatizer.lemmatize(w)
lems.append(w)
return lems
def get_df_tokens(df):
STEP = 2000
df_step = df[df.index<STEP]
i = 1
row = {}
while(len(df_step)):
text_array = df_step["text"]
text_array = text_array.as_matrix()
for text in text_array:
text_array = get_words(text)
tokens = get_tokens(text_array)
for token in tokens:
if token in row:
row[token] += 1
else:
row[token] = 1
df_step = df[(df.index >= i*STEP) & (df.index<(i+1)*STEP)]
i+=1
return row
def draw_tag_cloud(tokens):
list_of_couple = []
for key, value in tokens.iteritems():
list_of_couple.append((key, value))
list_of_couple.sort(key=lambda tup: tup[1], reverse=True)
wordcloud = WordCloud(background_color="white", max_words=200000, width=1000, height=700).generate_from_frequencies(list_of_couple)
plt.figure(figsize=(14, 10))
plt.imshow(wordcloud)
plt.axis("off")
plt.show()
Построим облако тегов для TIPS
In [301]:
tokens = get_df_tokens(tips_df)
draw_tag_cloud(tokens)
In [ ]:
tokens = get_df_tokens(tips_df)
draw_tag_cloud(tokens)
Построим облако тегов для REVIEW
In [306]:
reviews_df = pd.read_csv(PATH_TO_FOLDER+REVIEWS)
tokens = get_df_tokens(reviews_df)
draw_tag_cloud(tokens)