Created
November 26, 2018 00:55
-
-
Save erikrichardlarson/85c642fffc3ac78c7920bb48ecf18194 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from marketorestpython.client import MarketoClient | |
import pandas as pd | |
import numpy as np | |
class MarketoQueue: | |
def __init__(self, marketo_list_id='', munchkin_id='', | |
marketo_client_id='', marketo_client_secret='', fields=[]): | |
self.munchkin_id = munchkin_id | |
self.marketo_client_id = marketo_client_id | |
self.marketo_client_secret = marketo_client_secret | |
self.marketo_list = marketo_list_id | |
self.fields = fields | |
self.mc = MarketoClient(self.munchkin_id, self.marketo_client_id, self.marketo_client_secret) | |
def _build_queue(self): | |
leads = self.mc.execute(method='get_multiple_leads_by_list_id', | |
listId=self.marketo_list, | |
fields=self.fields) | |
self.lead_df = pd.DataFrame.from_dict(leads) | |
def _format_queue(self): | |
self.lead_df['fullName'] = self.lead_df['firstName'] + ' ' + self.lead_df['lastName'] | |
def receive_leads(self): | |
self._build_queue() | |
self._format_queue() | |
def _label_spam(self): | |
blacklisted_companies = pd.read_csv('./blacklisted_companies.txt').company.tolist() | |
self.lead_df['blacklisted_companies'] = np.where(self.lead_df.company.isin(blacklisted_companies), 1, 0) | |
blacklisted_names = pd.read_csv('./blacklisted_names.txt').fullName.tolist() | |
self.lead_df['blacklisted_names'] = np.where(self.lead_df.company.isin(blacklisted_names), 1, 0) | |
profane_words = pd.read_csv('./data/profane_words.txt').words.tolist() | |
self.lead_df['contains_profanity'] = np.where(self.lead_df.company.str.contains('|'.join(profane_words)), 1, 0) | |
self.lead_df['short_company_name'] = np.where(self.lead_df.company.str.len() == 1, 1, 0) | |
self.lead_df['numbers_in_name'] = np.where((self.lead_df['lastName'].str.count('\d+') \ | |
+ self.lead_df['firstName'].str.count('\d+')) > 1, 1, 0) | |
self.lead_df['first_last_null'] = np.where((self.lead_df.firstName.isnull()) & (self.lead_df.lastName.isnull()), 1, 0) | |
self.lead_df['first_equals_last'] = np.where(self.lead_df.firstName == self.lead_df.lastName, 1, 0) | |
def score_leads(self.lead_df): | |
self._label_spam() | |
self.lead_df.set_index('id', inplace=True) | |
self.lead_df['spam_score'] = (self.lead_df[[col for col in self.lead_df.columns if col not in self.fields]].sum(axis=1)) | |
self.spam_leads = self.lead_df[self.lead_df['spam_score'] >= 1] | |
def quick_detect(): | |
creds = utils.load_creds() | |
marketo_queue = MarketoQueue(marketo_list_id='', | |
munchkin_id='', | |
marketo_client_id='', | |
marketo_client_secret='', | |
fields=['id', 'email', 'firstName', | |
'lastName', 'company']) | |
marketo_queue.receive_leads() | |
marketo_queue.score_leads() | |
for record in marketo_queue.spam_leads.to_dict('records'): | |
# Update each Marketo record accordingly here | |
print(record) | |
if __name__ == '__main__': | |
quick_detect() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment