def main():
csv = pd.read_csv('city_aqi.csv')
print(csv[['City', 'AQI']].sort_values('AQI').head(4))
print(csv.info())
print(csv.head())
print('AQI最大值：', csv['AQI'].max())
print('AQI最小值：', csv['AQI'].min())
print('AQI均值：', csv['AQI'].mean())
top5_cities = csv.sort_values(by=['AQI']).head(5)
print('空气质量最好的5个城市：')
print(top5_cities)
top5_bottom_cities = csv.sort_values(by=['AQI'], ascending=False).head(5)
print('空气质量最差的5个城市：')
print(top5_bottom_cities)
print(csv[csv['AQI'] > 40])
top5_cities.plot(kind='bar',
x='City',
y='AQI',
title='空气质量最好的5个城市',
figsize=(10, 10))
plt.savefig('top5_aqi.png')
plt.show()
def uploaded():
error = None
filename = escape(session['csvname'])
if filename == None:
error = "Session error: filename is empty!"
return render_template('csvpreview.html', error=error)
# check for valid csv
try:
csv = CSVHandler(UPLOAD_FOLDER+"/"+filename)
except IOError:
return "File not found!"
except:
return "Unexpected error: " + sys.exc_info()[0]
data = csv.head(20)
# get ontology terms
allTerms=getOntologyClasses()
# app.logger.debug(">>>"+str(csv.NF))
# generate output
msg = "File ("+filename+") uploaded. Congratulations!"
# render template
r = render_template('csvpreview.html', msg=msg, data=data, terms=allTerms, ncols=csv.NF)
# close the CSV reader
csv.close()
return r
def __init__(self, file, mono=True, cap_train=None, sort=False):
if sort:
csv = pd.read_csv(file)
empty_counts = csv['puzzle'].apply(lambda p: p.count('0'))
csv['num_empty'] = empty_counts
csv.sort_values(by="num_empty", inplace=True)
if cap_train is not None:
csv = csv.head(cap_train)
self.data = csv
else:
self.data = pd.read_csv(file, nrows=cap_train)
self.mono = mono
self.cap_train = cap_train
self.edges = sudoku_edges()
api = tweepy.API(auth,wait_on_rate_limit=True)
#####United Airlines
# Open/Create a file to append data
csvFile = open('tweets.csv', 'w')
#Use csv Writer
csvWriter = csv.writer(csvFile)
for tweet in tweepy.Cursor(api.search,q="#ExploreMLBLR",count=100,
lang="en",
since="2019-10-03").items():
#print (tweet.created_at, tweet.text)
csvWriter.writerow([tweet.user.screen_name, tweet.text.encode('utf-8')])
csv = pd.read_csv('tweets.csv',names=["Username","Tweet"])
count = csv['Username'].value_counts()[:]
csv.head(10)
top2 = count.head(2)
top2
import matplotlib.pyplot as plt
colors = ["#E13F29", "#D69A80", "#D63B59", "#AE5552", "#CB5C3B", "#EB8076", "#96624E"]
top2.plot.pie(y=top2.index,
shadow=False,
colors=colors,
radius = 1000,
explode=(0, 0), # exploding 'Friday'
startangle=90,
autopct='%1.1f%%',
textprops={'fontsize': 10})
if __name__ == '__main__':
date_parser = lambda x: pd.datetime.strptime(x, '%Y-%m-%d %H:%M:%S')
directory = '2012'
files_names = os.listdir(directory)
csv_list = []
for name in files_names:
csv = pd.read_csv(
'%s/%s' % (directory, name),
# index_col=['id'],
parse_dates=['datetime'],
date_parser=date_parser,
encoding='utf-8',
)
csv_list.append(csv)
result = pd.concat(csv_list, sort=False, ignore_index=True)
# result.sort_index(inplace=True)
# result = result.drop('Unnamed: 0', 1)
result.sort_values(by='datetime', ascending=True, inplace=True)
result.to_csv('%s/tweets_bitcoin.csv' % directory, index=False)
csv = pd.read_csv('%s/tweets_bitcoin.csv' % directory,
# index_col=['id'],
parse_dates=['datetime'],
date_parser=date_parser,
encoding='utf-8')
print(csv.head())
print(len(csv))
f.write(str(follower) + '\n')
print("finished!")
break
except tweepy.TweepError as e:
print("error checking limits: %s" % e)
# remain_search_limits = 0
time.sleep(15 * 60)
# eg - applying function to a single user
collect_followers('BimAfolami') # it works!
BimAfolami = api.get_user('BimAfolami')
BimAfolami.followers_count #N = 8934
# check that length of this new followers_....csv corresponds to followers.count
csv = pd.read_csv('followers_BimAfolami.csv', header=None)
csv.head()
csv.shape #output: 8933 rows, 1 col - they NEARLY match...
# eg - try another one
collect_followers('JamesCleverly')
csv = pd.read_csv('followers_JamesCleverly.csv', header=None)
csv.head()
csv.shape # 73881, 1
JamesCleverly = api.get_user('JamesCleverly')
JamesCleverly.followers_count #N = 73881 - they match
########### 3 - apply collect_followers() to every elite, saving into separate files ###########
# Now I can run collect_followers() on every elite from filtered 'my_elites.csv' file
my_elites = pd.read_csv('my_elites.csv', index_col=0)
my_elites.shape # 420, 7