我正在尝试在Python中进行一些数据分析，我试图使用一些Twitter数据来查找不同国家/地区的推文数量。这是我正在使用的代码：
import json
import pandas as pd
import matplotlib.pyplot as plt
tweets_data=[]
with open('/home/surya/tweet.txt','r') as f:
for line in f:
try:
tweet= json.loads(line)
tweets_data.append(tweet)
except:
continue
tweet_table= pd.DataFrame()
tweet_table['country']= map(lambda tweet: tweet["place"]["country"] if tweet["place"] != None else None, tweets_data)
tweets_by_country = tweet_table['country'].value_counts()
fig, ax = plt.subplots()
ax.tick_params(axis='x', labelsize=15)
ax.tick_params(axis='y', labelsize=10)
ax.set_xlabel('Countries', fontsize=15)
ax.set_ylabel('Number of tweets' , fontsize=15)
ax.set_title('Top 5 countries', fontsize=15, fontweight='bold')
tweets_by_country[:5].plot(ax=ax, kind='bar', color='blue')
这产生了错误
KeyError "place"
所以我将代码修改为：
import json
import pandas as pd
import matplotlib.pyplot as plt
tweets_data=[]
def keyCheck(key,arr,default):
if key in arr.keys():
return arr[key]
else:
return default
with open('/home/surya/tweet.txt','r') as f:
for line in f:
try:
tweet= json.loads(line)
tweets_data.append(tweet)
except:
continue
tweet_table= pd.DataFrame()
tweet_table['country']= map(lambda tweet: tweet["place"]["country"] if keyCheck("place",tweet,"#default") != None else None, tweets_data)
tweets_by_country = tweet_table['country'].value_counts()
fig, ax = plt.subplots()
ax.tick_params(axis='x', labelsize=15)
ax.tick_params(axis='y', labelsize=10)
ax.set_xlabel('Countries', fontsize=15)
ax.set_ylabel('Number of tweets' , fontsize=15)
ax.set_title('Top 5 countries', fontsize=15, fontweight='bold')
tweets_by_country[:5].plot(ax=ax, kind='bar', color='blue')
但这导致了错误
AttributeError: list object has no attribute "keys"
我的数据格式为：
{"created_at":"Thu Jun 16 13:15:13 +0000 2016","id":743431739238932480,"id_str":"743431739238932480","text":"I fucking hate Ramsey #ENGWAL #EURO2016 https:\/\/t.co\/wkFqOu8iwf","source":"\u003ca href=\"http:\/\/twitter.com\/download\/iphone\" rel=\"nofollow\"\u003eTwitter for iPhone\u003c\/a\u003e","truncated":false,"in_reply_to_status_id":null,"in_reply_to_status_id_str":null,"in_reply_to_user_id":null,"in_reply_to_user_id_str":null,"in_reply_to_screen_name":null,"user":{"id":343618050,"id_str":"343618050","name":"SamuEars","screen_name":"S88Griff","location":"Derbados","url":null,"description":"27 years old, @RocesterFC1876 footballer, genuine, chilled out, opinionated, but most of all, wind up merchant","protected":false,"verified":false,"followers_count":496,"friends_count":272,"listed_count":1,"favourites_count":1915,"statuses_count":5505,"created_at":"Wed Jul 27 20:53:02 +0000 2011","utc_offset":null,"time_zone":null,"geo_enabled":true,"lang":"en","contributors_enabled":false,"is_translator":false,"profile_background_color":"C0DEED","profile_background_image_url":"http:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png","profile_background_image_url_https":"https:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png","profile_background_tile":false,"profile_link_color":"0084B4","profile_sidebar_border_color":"C0DEED","profile_sidebar_fill_color":"DDEEF6","profile_text_color":"333333","profile_use_background_image":true,"profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/636136111191031809\/aQyj3bgK_normal.jpg","profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/636136111191031809\/aQyj3bgK_normal.jpg","profile_banner_url":"https:\/\/pbs.twimg.com\/profile_banners\/343618050\/1409857726","default_profile":true,"default_profile_image":false,"following":null,"follow_request_sent":null,"notifications":null},"geo":null,"coordinates":null,"place":{"id":"232163114ebb8671","url":"https:\/\/api.twitter.com\/1.1\/geo\/id\/232163114ebb8671.json","place_type":"city","name":"Etwall","full_name":"Etwall, England","country_code":"GB","country":"United Kingdom","bounding_box":{"type":"Polygon","coordinates":[[[-1.608732,52.874969],[-1.608732,52.887677],[-1.594409,52.887677],[-1.594409,52.874969]]]},"attributes":{}},"contributors":null,"is_quote_status":false,"retweet_count":0,"favorite_count":0,"entities":{"hashtags":[{"text":"ENGWAL","indices":[22,29]},{"text":"EURO2016","indices":[30,39]}],"urls":[],"user_mentions":[],"symbols":[],"media":[{"id":743431733853433856,"id_str":"743431733853433856","indices":[40,63],"media_url":"http:\/\/pbs.twimg.com\/media\/ClEzORsWMAAlcQ3.jpg","media_url_https":"https:\/\/pbs.twimg.com\/media\/ClEzORsWMAAlcQ3.jpg","url":"https:\/\/t.co\/wkFqOu8iwf","display_url":"pic.twitter.com\/wkFqOu8iwf","expanded_url":"http:\/\/twitter.com\/S88Griff\/status\/743431739238932480\/photo\/1","type":"photo","sizes":{"small":{"w":680,"h":517,"resize":"fit"},"medium":{"w":1178,"h":896,"resize":"fit"},"thumb":{"w":150,"h":150,"resize":"crop"},"large":{"w":1178,"h":896,"resize":"fit"}}}]},"extended_entities":{"media":[{"id":743431733853433856,"id_str":"743431733853433856","indices":[40,63],"media_url":"http:\/\/pbs.twimg.com\/media\/ClEzORsWMAAlcQ3.jpg","media_url_https":"https:\/\/pbs.twimg.com\/media\/ClEzORsWMAAlcQ3.jpg","url":"https:\/\/t.co\/wkFqOu8iwf","display_url":"pic.twitter.com\/wkFqOu8iwf","expanded_url":"http:\/\/twitter.com\/S88Griff\/status\/743431739238932480\/photo\/1","type":"photo","sizes":{"small":{"w":680,"h":517,"resize":"fit"},"medium":{"w":1178,"h":896,"resize":"fit"},"thumb":{"w":150,"h":150,"resize":"crop"},"large":{"w":1178,"h":896,"resize":"fit"}}}]},"favorited":false,"retweeted":false,"possibly_sensitive":false,"filter_level":"low","lang":"en","timestamp_ms":"1466082913585"}
似乎问题是我的 tweet.txt 文件中某处“place”键无法使用。
有人可以建议解决方案，或者请指出我哪里出错了？
修改
我刚刚将代码更新到了
import json
import pandas as pd
import matplotlib.pyplot as mp
tweets_data=[]
with open('/home/surya/tweet.txt','r') as f:
for line in f:
try:
tweet= json.loads(line)
tweets_data.append(tweet)
except:
continue
tweet_table= pd.DataFrame()
tweet_table['country'] = map(lambda tweet: tweet['place']['country'] if 'place' in tweet is not None and 'country' in tweet['place'] is not None else None, tweets_data)
tweets_by_country = tweet_table['country'].value_counts()
fig, ax = plt.subplots()
ax.tick_params(axis='x', labelsize=15)
ax.tick_params(axis='y', labelsize=10)
ax.set_xlabel('Countries', fontsize=15)
ax.set_ylabel('Number of tweets' , fontsize=15)
ax.set_title('Top 5 countries', fontsize=15, fontweight='bold')
tweets_by_country[:5].plot(ax=ax, kind='bar', color='blue')
现在我收到了这个错误
TypeError: argument of type 'NoneType' is not iterable
更新
刚刚找到解决方案。仅当tweet中的'place'不是None时才附加tweets_data。因此
import json
import pandas as pd
import matplotlib.pyplot as plt
tweets_data=[]
with open('/home/surya/tweet.txt','r') as f:
for line in f:
try:
tweet= json.loads(line)
if 'place' in tweet is not None:
tweets_data.append(tweet)
except:
continue
tweet_table= pd.DataFrame()
tweet_table['country'] = [tweet['place']['country'] for tweet in tweets_data if tweet['place']]
tweets_by_country = tweet_table['country'].value_counts()
fig, ax = plt.subplots()
ax.tick_params(axis='x', labelsize=15)
ax.tick_params(axis='y', labelsize=10)
ax.set_xlabel('Countries', fontsize=15)
ax.set_ylabel('Number of tweets' , fontsize=15)
ax.set_title('Top 5 countries', fontsize=15, fontweight='bold')
tweets_by_country[:5].plot(ax=ax, kind='bar', color='blue')
plt.show()
答案 0 :(得分：1)
import json
import pandas as pd
import matplotlib.pyplot as plt
with open("testfile.txt", "r") as f:
tweet_data = [json.loads(line) for line in f]
tweet_table= pd.DataFrame()
tweet_table['country'] = [tweet['place']['country'] for tweet in tweet_data if tweet['place']]
tweets_by_country = tweet_table['country'].value_counts()
fig, ax = plt.subplots()
ax.tick_params(axis='x', labelsize=15)
ax.tick_params(axis='y', labelsize=10)
ax.set_xlabel('Countries', fontsize=15)
ax.set_ylabel('Number of tweets' , fontsize=15)
ax.set_title('Top 5 countries', fontsize=15, fontweight='bold')
tweets_by_country[:5].plot(ax=ax, kind='bar', color='blue')
plt.show()
好的，我发现了问题，因为推文总是包含一个地方作为json中的一个键，如果没有地方，那么该地方将为空，所以你只需要在尝试访问国家/地区之前，请确保地点不为空。这对我有用，但我只是在英国，因为数据只有1条推文与国家