def get_info_world(timeframe):
res_df = []
all_words = [['ada','altcoin','altcoins','bitcoin','bitconnect'],['bitminter', 'blockchain', 'blockchain%20mining','btc', 'cardano'],['crypto', 'cryptocurrencies','cryptocurrency', 'cryptographic', 'dash'], ['doge', 'dogecoin', 'eos','ethereum', 'hashing'],['hashocean', 'hodl', 'ico', 'iota', 'litecoin'],['localbitcoins', 'ltc', 'ltc', 'mercado', 'mining%20cryptocurrency'], ['montero', 'onecoin', 'satoshi', 'stellar', 'stratis'], ['tron', 'xlm', 'xmr', 'xrp', 'zcash']]
for k in all_words:
list_query_top = []
list_query_top_value = []
list_query_rising = []
list_query_rising_value = []
pytrend = TrendReq()
pytrend.build_payload(kw_list=k ,timeframe=timeframe)
related_queries_dict = pytrend.related_queries()
for f in k:
s_top = related_queries_dict[f]['top']
s_rising = related_queries_dict[f]['rising']
if s_rising is not None:
df_rising = s_rising.where(s_rising > 500)
df_rising = df_rising.dropna()
list_rising = df_rising['query'].tolist()
list_rising2 = df_rising['value'].tolist()
result_rising = zip(list_rising, list_rising2)
if s_top is not None:
df_top = s_top.where(s_top > 50)
df_top = df_top.dropna()
list_query_top = df_top['query'].tolist()
list_query_top2 = df_top['value'].tolist()
result_top = zip(list_query_top, list_query_top2)
print(list(result_top))
for j in result_top:
url = j[0].replace(" ", "+")
url2 = 'https://trends.'+'google.com/trends/explore?q=' + f + '+' + url + '&date={}'.format(timeframe)
pytrend.build_payload(kw_list=[j[0]],timeframe='now 1-d')
interest_by_region_df = pytrend.interest_by_region()
s = interest_by_region_df[j[0]]
df = s.where(s > 50)
df = df.dropna()
df = df.sort_values(ascending=False)
interest_by_region = pd.Series(df.index.values.tolist())
weight = pd.Series(list(df.values))
res_df.append(pd.DataFrame({'Location': pd.Series('Wordwide'), 'Keyword': pd.Series(f), 'Related Queries': pd.Series(j[0]), 'Percentage': pd.Series(str(j[1] * 10)), 'Interest by Region':interest_by_region, 'Weight': weight, 'Google Search Link': pd.Series('<a href="{}">{}</a>'.format(url2, url2))}))
for j in result_rising:
url = j[0].replace(" ", "+")
url2 = 'https://trends.'+'google.com/trends/explore?q=' + f + '+' + url + '&date={}'.format(timeframe)
pytrend.build_payload(kw_list=[j[0]],timeframe=timeframe)
interest_by_region_df = pytrend.interest_by_region()
s = interest_by_region_df[j[0]]
df = s.where(s > 50)
df = df.dropna()
df = df.sort_values(ascending=False)
interest_by_region = pd.Series(df.index.values.tolist())
weight = pd.Series(list(df.values))
res_df.append(pd.DataFrame({'Location': pd.Series('Wordwide'), 'Keyword': pd.Series(f), 'Related Queries': pd.Series(j[0]), 'Percentage': pd.Series('Breakout'), 'Interest by Region':interest_by_region, 'Weight': weight, 'Google Search Link': pd.Series('<a href="{}">{}</a>'.format(url2, url2))}))
df = pd.concat(res_df)
return df
def find_geos(tf, phrase):
pytrends = TrendReq(hl='en-US', tz=360)
pytrends.build_payload([phrase],
cat=0,
timeframe='now 7-d',
geo='',
gprop='')
print(type(pytrends.interest_by_region(resolution='COUNTRY')))
return pytrends.interest_by_region(resolution='COUNTRY')
def get_query_features_GoogleTrends(participant_name,
hl='en-US',
geo="",
gprop=""):
#https:/towardsdatascience.com/telling-stories-with-google-trends-using-pytrends-in-python-a11e5b8a177
#download imgs agosto 2020
#SPAIN
# pytrends = TrendReq(hl='es-ES', tz=360, geo="ES")
# df_by_region_SPAIN = pytrends.interest_by_region(resolution='REGION', inc_low_vol=True, inc_geo_code=True)
#WORLD
# '2020-06-01 2017-06-01' example '2016-12-14 2017-01-25'
pytrends = TrendReq(hl=hl, tz=360, geo=geo)
pytrends.build_payload([participant_name],
cat=0,
timeframe='2017-06-01 2020-06-01',
geo=geo,
gprop=gprop)
df_over_time = pytrends.interest_over_time()
query_popularity_by_country = pytrends.interest_by_region(
resolution='COUNTRY', inc_low_vol=True, inc_geo_code=True)
query_popularity_by_country["COUNTRY"] = query_popularity_by_country.index
query_popularity_by_country.index = range(len(query_popularity_by_country))
query_popularity_by_country = query_popularity_by_country.sort_values(
[participant_name], ascending=False)
#dict_related_topic = pytrends.related_topics()
#suggestions = pytrends.suggestions(participant_name)
#N_COUNTRIES:
# result_higher50 = query_popularity_by_country[query_popularity_by_country[participant_name]>=50]
# result_lower50 = query_popularity_by_country[query_popularity_by_country[participant_name] < 50]
return query_popularity_by_country
def get_interest_by_region(sessiontrend=None,
term='',
geo='GB',
timeframe='today 5-y',
resolution="COUNTRY"):
kw_list = [term]
if sessiontrend is None:
pytrends = TrendReq(hl='en-US', tz=0)
pytrends.build_payload(kw_list,
cat=0,
timeframe=timeframe,
geo=geo,
gprop='')
else:
pytrends = sessiontrend
top_regions = pytrends.interest_by_region(resolution=resolution,
inc_low_vol=True,
inc_geo_code=False)
region_names = list(top_regions[term])
region_score = list(top_regions.index.values)
#print("Debug region stuff: ", region_names, region_score)
result = []
for i in range(len(region_names)):
result.append([region_names[i], region_score[i]])
result = sorted(result, key=lambda l: l[0], reverse=True)
i = range(len(result))
for i in range(len(result)):
if result[i][0] == 0:
break
return result[:i]
def get_trends(kw_list: list, s_date, e_date):
"""
Gets trends from Google Trends and returnds pandas series table.
:param kw_list: list, keyword list.
:param s_date: date, start_date.
:parma e_date: date, end_date.
"""
try:
pytrends = TrendReq(hl='tr_TR', tz=360)
if kw_list[-1] == '':
kw_list.pop(-1)
if s_date is None or s_date == "" or e_date is None or e_date == "":
pytrends.build_payload(kw_list, cat=0, timeframe='all', geo='TR')
else:
pytrends.build_payload(kw_list, cat=0, timeframe='''{s_date} {e_date}'''.format(s_date=str(s_date), e_date=str(e_date)), geo='TR')
trends_data = pytrends.interest_by_region(resolution='CITY')
trends_data.to_csv('trends_data.csv')
# json_data = trends_data.to_json(orient="columns", force_ascii=False)
except Exception as e:
raise e
return trends_data
def generate_state_level_data_proxies(kw_list_, start_date, end_date, proxies_):
previous_date = ''
df = pd.DataFrame()
pytrend = TrendReq(hl='en-US', tz=360, timeout=(10, 25), proxies=proxies_, retries=5,
backoff_factor=1)
for current_date in daterange(start_date, end_date):
print(current_date)
if previous_date == '':
previous_date = current_date
continue
timeframe_ = previous_date.strftime(date_time_format_string) + ' ' + current_date.strftime(
date_time_format_string)
interest_list = []
count = 1
for entry in kw_list_:
if count % 25 == 0:
print(count)
new_kw_list = [entry]
pytrend.build_payload(kw_list=new_kw_list, geo='US', timeframe=timeframe_)
interest_by_region_df = pytrend.interest_by_region(resolution='Region')
interest_list.append(interest_by_region_df)
count += 1
df[previous_date.strftime(date_time_format_string)] = interest_list
previous_date = current_date
return df
async def google_trends(request):
if request.method == 'GET':
topic = request.args.get('topic').split(',')
lang = request.args.get('lang')
region = request.args.get('reg')
else:
return json({'response': False, 'message': 'Wrong HTTP method', 'results': []})
if topic is None or topic is '':
return json({'response': False, 'message': 'Not enough arguments', 'results': []})
from pytrends.request import TrendReq
pytrends = TrendReq(hl='{}-{}'.format(lang, region), tz=360)
pytrends.build_payload(topic)
res = pytrends.interest_over_time()
res.drop('isPartial', axis=1, inplace=True)
rel_topics = pytrends.related_topics()[topic[0]]
rel_topics.drop('mid', axis=1, inplace=True)
rel_queries = pytrends.related_queries()[topic[0]]
countries = pytrends.interest_by_region(resolution='COUNTRY')
countries = countries[(countries.T != 0).any()]
from json import loads
countries = loads(countries.to_json())[topic[0]]
return json({'message':'done', 'response': True, 'result': {'interest': res.to_json(), 'related_topics': rel_topics.to_json(),
'top_queries': rel_queries['top'].to_json(), 'rising_queries': rel_queries['rising'].to_json(), 'countries': countries}})
def home(request):
location = "US"
location = request.POST.get("geo", "")
# Only need to run this once, the rest of requests will use the same session.
pytrend = TrendReq()
# Create payload and capture API tokens. Only needed for interest_over_time(), interest_by_region() & related_queries()
pytrend.build_payload(kw_list=['anime'], geo=location, cat=317)
# Interest Over Time
interest_over_time_df = pytrend.interest_over_time()
interest_df = interest_over_time_df.tail(10)
interest_array = []
for m in interest_df.iterrows():
interest_array.append([m[0], m[1][0]])
# anime interest by regions in US
interest_by_region_df = pytrend.interest_by_region()
sorted_df = interest_by_region_df.sort_values(['anime'],
ascending=False).head(10)
region_array = []
# Convert df to array
for i in sorted_df.iterrows():
parsed_row = int(i[1][0])
region_array.append([i[0], parsed_row])
return render(request, "main/view.html", {
"regions": region_array,
"interest": interest_array,
"location": location
})
class Trends:
def __init__(self, keywords):
self.pytrends = TrendReq(hl='uk', tz=360)
self.pytrends.build_payload(keywords)
def interest_over_time(self):
return self.pytrends.interest_over_time()
def interest_by_region(self, resolution='COUNTRY', inc_low_vol=False):
return self.pytrends.interest_by_region(resolution=resolution,
inc_low_vol=inc_low_vol)
def related_topics(self):
return self.pytrends.related_topics()
def related_querries(self):
return self.pytrends.related_queries()
def trending_searches(self, pn='ukraine'):
return self.pytrends.trending_searches(pn=pn)
def top_charts(self, date, hl='uk', tz=360, geo='GLOBAL'):
return self.pytrends.top_charts(date, hl=hl, tz=tz, geo=geo)
def suggestions(self, keyword):
return self.pytrends.suggestions(keyword)
def two_a_search(m1, m2, m3):
search = []
pytrend = TrendReq()
search.append(m1)
search.append(m2)
pytrend.build_payload(search, geo='IN', timeframe='today 3-m')
result_total = pytrend.interest_over_time()
result_total_geo = pytrend.interest_by_region(resolution='COUNTRY',
inc_low_vol=True,
inc_geo_code=False)
index_list = list(map(lambda x: str(x), result_total.tail(30).index))
index_list = list(
map(
lambda x: str(
datetime.strptime(x, "%Y-%m-%d %H:%M:%S").strftime("%d-%b")),
index_list))
m1_3m = list(result_total[m1].tail(30))
m2_3m = list(result_total[m2].tail(30))
index_list_geo_1 = list(result_total_geo[m1].nlargest(10).index)
index_list_geo_2 = list(result_total_geo[m2].nlargest(10).index)
m1_geo = list(result_total_geo[m1].nlargest(10).values)
m2_geo = list(result_total_geo[m2].nlargest(10).values)
m1_key = list(pd.DataFrame(pytrend.suggestions(m1))["title"].values)
m2_key = list(pd.DataFrame(pytrend.suggestions(m2))["title"].values)
size = len(search)
return (m1_3m, m2_3m, index_list, m1, m2, m3, size, m1_geo, m2_geo,
index_list_geo_1, index_list_geo_2, m1_key, m2_key)
def google_trends_data(kw_list=None, start_string='2004-01-01', end_string=None, resolution='REGION'):
pytrend = TrendReq()
date_list = pd.date_range(start_string, end_string, freq='1M') - pd.offsets.MonthBegin(1)
data_list = []
for index, dt in enumerate(date_list):
next_dt = index + 1
if next_dt < len(date_list):
timeframe = dt.strftime('%Y-%m-%d') + ' ' + date_list[next_dt].strftime('%Y-%m-%d')
print("DATE:", timeframe)
pytrend.build_payload(kw_list, cat=0, timeframe=timeframe, geo='US', gprop='')
# Interest by region
# DMA ~ MAJOR CITY, REGION == STATE
_df = pytrend.interest_by_region(
resolution=resolution
) # metro level data ( you can change 'DMA' to 'CITY', 'REGION' )
_df.reset_index(inplace=True)
_df.loc[:, 'date'] = dt
print(_df.head())
print("\n\n")
data_list.append(_df)
df = pd.concat(data_list)
print(df.shape)
## columns w/ spaces to _
df.columns = df.columns.str.replace(' ', '_')
df.columns = map(str.lower, df.columns)
return df
def get_data(keyword, trend_type):
data = {}
# Connect to Google
pytrend = TrendReq(hl='en-US', tz=360)
# Build Payload for pytrends
pytrend.build_payload(kw_list=[keyword],
geo='US',
timeframe='today 3-m',
cat=0,
gprop='')
# get the data from the api if intereset_by_region or get_historical_interest
if trend_type == 'interest_by_region':
data = pytrend.interest_by_region(inc_geo_code=True)
# get the geo data for regions
geo = data.to_dict()['geoCode']
# get the interest for the search keyword
data = data.to_dict()[keyword]
data = [geo, data]
print(data)
elif trend_type == 'get_historical_interest':
data = pytrend.interest_over_time()
data = data.to_dict()[keyword]
print(data)
print("data")
return data
def by_region(kw_list, draw=True, drop_0=True, **kwargs):
"""
Fetches the DataFrame of the Google Trend for a list of keywords. By
default, it will drop 0 values and will draw the plot.
Parameters
----------
kw_list : list
List of keywords to search.
draw : bool, optional
Draw the bar plot for the keywords or not. The default is True.
drop_0 : bool, optional
Drop empty rows. The default is True.
Returns
-------
pandas.DataFrame
DataFrame containing the keywords as columns and the country as index.
"""
pytrend = TrendReq()
pytrend.build_payload(kw_list=kw_list, **kwargs)
df = pytrend.interest_by_region()
if drop_0:
df = df.loc[(df!=0).any(axis=1)]
if draw:
df.plot(kind='bar')
return df
def pytrend_data(kw_list):
if len(kw_list) == 1:
pytrend = TrendReq()
pytrend.build_payload(kw_list=kw_list)
df = pytrend.interest_by_region().reset_index()
df = df[df[kw_list[0]] != 0].reset_index(drop=True)
else:
print("List can only have one value.")
return pytrend, df
def getByDate(self, topic, dateVal):
google_username = "******"
google_password = "******"
pytrend = TrendReq(google_username,
google_password,
custom_useragent='My Pytrends Script')
pytrend.build_payload(kw_list=[topic], geo='US', timeframe=dateVal)
dat = pytrend.interest_by_region(resolution='CITY')
dat = dat.drop(['District of Columbia'])
return dat
def plottrends(searchterm, tf, booRegion, booCreateCSV, secondtermforseries):
print('Importing data from Google Trends')
pytrend = TrendReq()
if booRegion or len(secondtermforseries) == 0:
search_list = [searchterm]
else:
search_list = [searchterm, secondtermforseries]
pytrend.build_payload(search_list, cat=0, timeframe=tf, geo='', gprop='')
register_matplotlib_converters()
plt.figure(figsize=(10, 6))
fig = plt.figure(1)
if booRegion:
df = pytrend.interest_by_region()
df.sort_values(searchterm, inplace=True, ascending=True)
df.reset_index(level=0, inplace=True)
df = df.tail(25)
ax = fig.add_subplot(111)
ax.tick_params(axis='x', which='major', labelsize=6)
ax.tick_params(axis='x', which='minor', labelsize=6)
ax.set_xticklabels(df['geoName'], rotation=50, ha="right")
plt.bar(df['geoName'], df[searchterm], color='grey')
plt.title("'" + searchterm + "'" +
' google searches by country over time : ' + tf)
else:
df = pytrend.interest_over_time()
df.reset_index(level=0, inplace=True)
plt.ylabel('Index')
plt.plot(df['date'], df[searchterm], color='black', label=searchterm)
if len(secondtermforseries) > 0:
plt.plot(df['date'],
df[secondtermforseries],
color='grey',
label=secondtermforseries)
searchterm = searchterm + ' \\ ' + secondtermforseries
plt.legend(loc="upper left")
plt.title("'" + searchterm + "'" + ' google searches through time : ' +
tf)
print(df.head())
if booCreateCSV:
print('Creating csv file')
df.to_csv('c:\\temp\\googletrends.csv')
plt.show()
class Trends:
'''
Wrapper class for pytrends library.
'''
def __init__(self, keywords):
'''
Initialize trends object.
'''
self.pytrends = TrendReq(hl='uk', tz=360)
self.pytrends.build_payload(keywords)
def interest_over_time(self):
'''
Get interest overt time.
'''
return self.pytrends.interest_over_time()
def interest_by_region(self, resolution='COUNTRY', inc_low_vol=False):
'''
Get interest by region.
'''
return self.pytrends.interest_by_region(resolution=resolution, inc_low_vol=inc_low_vol)
def related_topics(self):
'''
Get related topics.
'''
return self.pytrends.related_topics()
def related_querries(self):
'''
Get related search querries.
'''
return self.pytrends.related_queries()
def trending_searches(self, pn='ukraine'):
'''
Get trending searhes by country.
'''
return self.pytrends.trending_searches(pn=pn)
def top_charts(self, date, hl='uk', tz=360, geo='GLOBAL'):
'''
Get top charts by date.
'''
return self.pytrends.top_charts(date, hl=hl, tz=tz, geo=geo)
def suggestions(self, keyword):
'''
Get suggestions for keyword.
'''
return self.pytrends.suggestions(keyword)
def getGoogleTrendData2(geoCode):
pytrend = TrendReq(hl='en-US', tz=360)
kw_list = ['flu']
pytrend.build_payload(kw_list,
cat=0,
timeframe='today 1-m',
geo=geoCode,
gprop='')
output = pytrend.interest_by_region(resolution='CITY')
return output.to_dict()
def retrieveData(value):
pytrend = TrendReq()
kw_list = [value]
pytrend.build_payload(kw_list,
cat=0,
geo='ZA',
gprop='',
timeframe='now 7-d')
interest_over_time_df = pytrend.interest_over_time()
interest_by_region_df = pytrend.interest_by_region()
return [interest_over_time_df, interest_by_region_df]
def google_trend_score_of_phrase(phrase):
pytrends = TrendReq(hl='en-US', tz=360)
pytrends.build_payload([phrase],
cat=0,
timeframe='today 5-y',
geo='',
gprop='')
popularity_of_phrase_by_state = pytrends.interest_by_region(
resolution='USA')
popularity_score = popularity_of_phrase_by_state.sum().values[0]
return [phrase, popularity_score]
class Trends:
def __init__(self, name: str):
self.name = name
self.trends = TrendReq(hl='uk', tz=360)
self.trends.build_payload([name])
def get_interest_over_time(self):
dataframe = self.trends.interest_over_time()
return dataframe[dataframe[self.name] > 0][self.name].to_dict()
def get_countries(self):
dataframe = self.trends.interest_by_region()
return dataframe[dataframe[self.name] > 0][self.name].to_dict()
def getGtrendsRegionalStat(self, request, country='ru_RU'):
pytrends = TrendReq(hl=country, tz=360, timeout=(10,25),
#proxies=['https://34.203.233.13:80',],
retries=2, backoff_factor=0.4)
pytrends.build_payload(kw_list=[request])
interest_by_region_df = pytrends.interest_by_region()
result = []
for k,v in interest_by_region_df.items():
result.append({
'region' : k,
'count' : v
})
return result
def regions(other_args: List[str], ticker: str):
"""Plot bars of regions based on stock's interest. [Source: Google]
Parameters
----------
other_args : List[str]
Command line arguments to be processed with argparse
ticker : str
Ticker
"""
parser = argparse.ArgumentParser(
add_help=False,
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
prog="regions",
description=
"""Plot bars of regions based on stock's interest. [Source: Google]""",
)
parser.add_argument(
"-n",
"--num",
action="store",
dest="n_num",
type=check_positive,
default=10,
help="number of regions to plot that show highest interest.",
)
try:
ns_parser = parse_known_args_and_warn(parser, other_args)
if not ns_parser:
return
pytrend = TrendReq()
pytrend.build_payload(kw_list=[ticker])
df_interest_region = pytrend.interest_by_region()
df_interest_region = df_interest_region.sort_values(
[ticker], ascending=False).head(ns_parser.n_num)
plt.figure(figsize=(25, 5))
plt.title(f"Top's regions interest on {ticker}")
plt.bar(df_interest_region.index,
df_interest_region[ticker],
width=0.8)
plt.grid(b=True, which="major", color="#666666", linestyle="-")
plt.ylabel("Interest [%]")
plt.xlabel("Region")
plt.show()
print("")
except Exception as e:
print(e, "\n")
def value_analysis():
google_username = "******"
google_password = "******"
path = ""
print "hello begin please"
pytrend = TrendReq(google_username,
google_password,
custom_useragent='My Pytrends Script')
# Create payload and capture API tokens. Only needed for interest_over_time(), interest_by_region() & related_queries()
pytrend.build_payload(kw_list=['OPEC'], timeframe='now 7-d')
# Interest Over Time
interest_over_time_df = pytrend.interest_over_time()
print interest_over_time_df
interest_by_region_df = pytrend.interest_by_region()
print interest_by_region_df
def lambda_handler(event, context):
old_df = pd.read_csv("s3://open-hr-google-trends/region.csv")
pytrends = TrendReq(hl='es-MX', tz=360)
kw_list = ["bolsa de trabajo"]
pytrends.build_payload(kw_list, timeframe='now 7-d', geo='MX', gprop='')
regions = pytrends.interest_by_region(resolution='REGION', inc_low_vol=True, inc_geo_code=False)
regions.reset_index(inplace=True)
regions["date"] = str(date.today())
regions[["date", "geoName", "bolsa de trabajo"]]
regions.rename(columns = {"geoName": "geoname", "bolsa de trabajo": "bolsa_de_trabajo"}, inplace = True)
df = old_df.append(regions)
bucket = 'open-hr-google-trends'
csv_buffer = StringIO()
df.to_csv(csv_buffer, index = False)
s3_resource.Object(bucket, 'region.csv').put(Body=csv_buffer.getvalue())
def get_data(self):
pytrend = TrendReq()
keywords = self.keyword_list
pytrend.build_payload(kw_list=keywords,
cat=0,
timeframe=self.timeframe,
geo='',
gprop='')
data = pytrend.interest_by_region(resolution='COUNTRY',
inc_low_vol=True,
inc_geo_code=True)
data.reset_index(inplace=True)
data = data.replace(0, np.nan)
return data
def get_regions(ticker: str) -> pd.DataFrame:
"""Get interest by region from google api [Source: google]
Parameters
----------
ticker : str
Ticker to look at
Returns
-------
pd.DataFrame
Dataframe of interest by region
"""
pytrend = TrendReq()
pytrend.build_payload(kw_list=[ticker])
return pytrend.interest_by_region()
def main(keywords: List[str],
geo: str = "NL") -> None:
""" Runner """
pytrend = TrendReq()
pytrend.build_payload(kw_list=keywords, geo=geo)
# Interest Over Time
interest_over_time_df = pytrend.interest_over_time()
pprint(interest_over_time_df.tail())
# Interest by Region
interest_by_region_df = pytrend.interest_by_region()
print(interest_by_region_df.head())
# Related Queries, returns a dictionary of dataframes
related_queries_dict = pytrend.related_queries()
print(related_queries_dict)
def regions(l_args, s_ticker):
parser = argparse.ArgumentParser(
prog='regions',
description=
"""Plot bars of regions based on stock's interest. [Source: Google]""")
parser.add_argument(
'-n',
"--num",
action="store",
dest="n_num",
type=check_positive,
default=10,
help='number of regions to plot that show highest interest.')
try:
(ns_parser, l_unknown_args) = parser.parse_known_args(l_args)
if l_unknown_args:
print(
f"The following args couldn't be interpreted: {l_unknown_args}\n"
)
return
pytrend = TrendReq()
pytrend.build_payload(kw_list=[s_ticker])
df_interest_region = pytrend.interest_by_region()
df_interest_region = df_interest_region.sort_values(
[s_ticker], ascending=False).head(ns_parser.n_num)
plt.figure(figsize=(25, 5))
plt.title(f"Top's regions interest on {s_ticker}")
plt.bar(df_interest_region.index,
df_interest_region[s_ticker],
width=0.8)
plt.grid(b=True, which='major', color='#666666', linestyle='-')
plt.ylabel('Interest [%]')
plt.xlabel("Time")
plt.show()
print("")
except:
print("")
def compute_search_penalty_country_dict(neg_terms, save_as="sp_dict.pkl"):
s_t = [i for i in neg_terms.keys()]
pytrend = TrendReq()
pytrend.build_payload(kw_list=s_t) # Interest by Region
df = pytrend.interest_by_region()
country_penalty_dict = {}
for i in df.iterrows():
country = i[0]
total_penalty = 0
for s_t_idx in range(len(s_t)):
search_intrest = i[1][s_t_idx]
total_penalty += search_intrest * neg_terms[
s_t[s_t_idx]] #multiply the penalty by the search term intrest
country_penalty_dict.update({country: total_penalty})
print("saving country_penalty_dict as", save_as)
with open(save_as, 'wb+') as handle:
pkl.dump(country_penalty_dict, handle, protocol=pkl.HIGHEST_PROTOCOL)
return country_penalty_dict
from pytrends.request import TrendReq # Login to Google. Only need to run this once, the rest of requests will use the same session. pytrend = TrendReq() # Create payload and capture API tokens. Only needed for interest_over_time(), interest_by_region() & related_queries() pytrend.build_payload(kw_list=['pizza', 'bagel']) # Interest Over Time interest_over_time_df = pytrend.interest_over_time() print(interest_over_time_df.head()) # Interest by Region interest_by_region_df = pytrend.interest_by_region() print(interest_by_region_df.head()) # Related Queries, returns a dictionary of dataframes related_queries_dict = pytrend.related_queries() print(related_queries_dict) # Get Google Hot Trends data trending_searches_df = pytrend.trending_searches() print(trending_searches_df.head()) # Get Google Top Charts top_charts_df = pytrend.top_charts(cid='actors', date=201611) print(top_charts_df.head()) # Get Google Keyword Suggestions suggestions_dict = pytrend.suggestions(keyword='pizza')
def test_interest_by_region(self):
pytrend = TrendReq()
pytrend.build_payload(kw_list=['pizza', 'bagel'])
self.assertIsNotNone(pytrend.interest_by_region())
