\t, \r, and \n
+# # install unidecode
+# ! pip install unidecode
+
+# # install pandas-redshift library if not already installed
+# ! pip install pandas-redshift
+import os
+from collections import Counter
+import io
+import boto3
+import pandas as pd
+import numpy as np
+import pandas_redshift as pr
+# pandas display settings
+pd.set_option("display.max_columns", 999)
+pd.set_option("display.max_rows", 999)
+import unidecode
+import re
+
+print(os.listdir(os.path.join('..', 'data')))
+
+# create path to tsv file
+path_to_tsv = os.path.join('..', 'data', 'data.tsv')
+
+# read each line of file into a list, challenge documentation said 'utf-16-le' encoding
+# https://realpython.com/read-write-files-python/
+# https://stackoverflow.com/questions/4190683/python-string-replace-for-utf-16-le-file
+with open(path_to_tsv, 'r', encoding='utf-16-le') as f:
+ ls_lines_tsv_utf16le = f.readlines()
+# remove accents on characters
+# https://stackoverflow.com/questions/517923/what-is-the-best-way-to-remove-accents-normalize-in-a-python-unicode-string
+# https://medium.com/@randombites/how-to-handle-accented-special-strings-175e65d96123
+# https://stackoverflow.com/questions/31207287/converting-utf-16-to-utf-8
+ls_lines_tsv = [unidecode.unidecode(x) for x in ls_lines_tsv_utf16le]
+print(f'Number of lines in file: {len(ls_lines_tsv)}\n\n')
+
+# print a few lines
+for idx, each_line in enumerate(ls_lines_tsv[:5]):
+ print(idx, each_line)
+# challenge documentation says tab delimiters, same number of fields per line ...
+# count number of tab delimiters per line
+# https://www.programiz.com/python-programming/methods/string/count
+ls_num_tabdelim = [x.count('\t') for x in ls_lines_tsv]
+
+# what is frequency of num_tabs per line?
+# https://stackoverflow.com/questions/2600191/how-can-i-count-the-occurrences-of-a-list-item
+# https://www.w3schools.com/python/ref_func_sorted.asp
+counter_numtabs = Counter(ls_num_tabdelim)
+for x in sorted(counter_numtabs.items(), reverse=True):
+ print(x)
+def count_num_per_item(ls_input, str_input):
+ '''
+ Count number of occurrences per item in list.
+ Using this function to read a text file into a list and search for anomalies.
+ Print the results, and output the counter-dictionary.
+
+ For example, search the number of:
+ * tabs per item string
+ * newline characters per item string
+
+ Dependencies:
+ from collections import Counter
+
+ Input:
+ ls_input - list, output of file.readlines()
+ str_input - str, searching for substring
+ Return:
+ counter_num_per_item - Counterobject, looks like a dictionary,
+ where key is number of occurances per item,
+ and value is number of items of this occurance
+ '''
+
+ # list of number of occurences per item
+ ls_num_occurences_per_item = [x.count(str_input) for x in ls_input]
+
+ # check frequency of occurences
+ counter_num_per_item = Counter(ls_num_occurences_per_item)
+
+ # print out frequency of occurences
+ print(f'Total number of items in list: {len(ls_input)}\n')
+ print(f'Frequency of occurences:')
+ _ = [print(x) for x in sorted(counter_num_per_item.items(), reverse=True)]
+
+ return counter_num_per_item
+# not all of the lines have 4 tab-delimiters
+_ = count_num_per_item(ls_lines_tsv, '\t')
+# almost all lines have newline char
+_ = count_num_per_item(ls_lines_tsv, "\n")
+# surprised none of lines have double-quote
+_ = count_num_per_item(ls_lines_tsv, '\"')
+# surprised none of lines have single-quote
+_ = count_num_per_item(ls_lines_tsv, "\'")
+# none of lines have carriage-return
+_ = count_num_per_item(ls_lines_tsv, "\r")
+# 6 of the lines have 1 dash
+_ = count_num_per_item(ls_lines_tsv, "-")
+# one of the lines have 1 slash
+_ = count_num_per_item(ls_lines_tsv, "/")
+# most items have 4 tab-delimters; anomalies don't have 4 tab-delimiters
+# view lines with anomalies '\t', print out line number (0-index)
+_ = [print(f'Line number {idx} => ', item) for idx, item in enumerate(ls_lines_tsv) if item.count('\t') != 4]
+# view lines with anomalies on '\n' ... this is the last line in the data file
+_ = [print(f'Line number {idx} ... ', item) for idx, item in enumerate(ls_lines_tsv) if item.count('\n') != 1]
+# view lines with anomalies on '-' ... 5 out of 6 are in the account_number, one is in the last_name
+_ = [print(f'Line number {idx} ... ', item) for idx, item in enumerate(ls_lines_tsv) if item.count('-') > 0]
+# view lines with anomalies on '/' ... one account number
+_ = [print(f'Line number {idx} ... ', item) for idx, item in enumerate(ls_lines_tsv) if item.count('/') > 0]
+Section 1:¶
+# create list with only items with 4 tabs
+ls_lines_tsv_4tabs = [x for x in ls_lines_tsv if x.count('\t')==4]
+
+# convert list to string, already has newline character, no need to add to join
+str_lines_tsv_4tabs = ''.join(ls_lines_tsv_4tabs)
+
+# convert str to io.StringIO object so it can be read as CSV file
+# https://www.kite.com/python/answers/how-to-create-a-pandas-dataframe-from-a-string-in-python
+io_data_tsv = io.StringIO(str_lines_tsv_4tabs)
+
+# create dataframe, tab-delimited
+df_4_tabs = pd.read_csv(io_data_tsv, sep='\t')
+
+print(f"Shape of dataframe: {df_4_tabs.shape}")
+df_4_tabs.head()
+print(df_4_tabs.nunique())
+# how many null values per column
+print(df_4_tabs.isna().sum())
+print(df_4_tabs.dtypes)
+# is the account_number always numeric?
+print('Number of records in dataframe: ', df_4_tabs.shape[0])
+print('Number of records `account_number` is numeric: ', df_4_tabs['account_number'].str.isnumeric().sum())
+# examine rows with null first_name or last_name
+mask_null_name = (
+ df_4_tabs['first_name'].isna()
+ | df_4_tabs['last_name'].isna()
+)
+df_4_tabs.loc[mask_null_name]
+# create columns with flags on null names
+df_4_tabs['null_firstname'] = df_4_tabs['first_name'].isna()
+df_4_tabs['null_lastname'] = df_4_tabs['last_name'].isna()
+df_4_tabs['null_name'] = df_4_tabs['null_firstname'] | df_4_tabs['null_lastname']
+
+# create column with length of account_number
+df_4_tabs['len_acct_num'] = df_4_tabs['account_number'].apply(len)
+
+# create column with email domain name
+# https://stackoverflow.com/questions/12504976/get-last-column-after-str-split-operation-on-column-in-pandas-dataframe
+df_4_tabs['domain_name'] = df_4_tabs['email'].str.split('@').str[-1]
+df_4_tabs.head()
+# examine each column for number of unique values ...
+# ... look for .value_counts() situations where there are fewer than 10 counts per column
+# print out number of unique values per column if > 10, print out .value_counts() if < 10
+print(f'Shape of dataframe: {df_4_tabs.shape}\n')
+print(f'Columns in dataframe: \n{list(df_4_tabs.columns)}\n')
+
+for each_col in df_4_tabs.columns:
+ num_counts = df_4_tabs[each_col].value_counts().shape[0]
+ print(f'*** Number of value counts in column: {each_col} ===> {num_counts}\n')
+
+ if num_counts < 10:
+ print(f'Value counts of column: {each_col}')
+ print(df_4_tabs[each_col].value_counts())
+ print()
+# most values in account_number field are 6 characters long ... anomalies are not ...
+# ... examine records where account number is not 6 digits long
+df_4_tabs.query(" len_acct_num != 6 ")
+# examine non-numeric account numbers by creating separate dataframe
+# https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.Series.str.isnumeric.html
+mask_numeric_acct_num = df_4_tabs['account_number'].str.isnumeric()
+df_4_tabs_nonnumeric_acct_num = df_4_tabs.loc[~mask_numeric_acct_num]
+
+print('Show dataframe of non-numeric account numbers: \n')
+display(df_4_tabs_nonnumeric_acct_num)
+print()
+
+print('Show the actual account_numbers: ')
+print(df_4_tabs_nonnumeric_acct_num['account_number'].values)
+# reasons account_number non-numeric: leading/trailing whitespace, dash, slash ...
+# ... clean up the account number, remove space and dashes and slashes => save as new column
+df_4_tabs['clean_account_number'] = df_4_tabs['account_number'].str.replace(' ', '').str.replace('-', '').str.replace('/', '')
+
+# in new clean column, any account numbers less than 6 digits? create new column to measure length
+df_4_tabs['len_clean_acct_num'] = df_4_tabs['clean_account_number'].apply(len)
+
+print('Number of characters in `clean_account_number` column: ')
+print(df_4_tabs['len_clean_acct_num'].value_counts())
+print()
+
+print('Show the `clean_account_number` that is not 6 characters long: ')
+print(df_4_tabs.query(" len_clean_acct_num != 6 ")['clean_account_number'].values)
+# check for anomalies on first or last character of account number
+df_4_tabs['first_char_clean_an'] = df_4_tabs['clean_account_number'].str[0]
+df_4_tabs['last_char_clean_an'] = df_4_tabs['clean_account_number'].str[-1]
+
+display(df_4_tabs['first_char_clean_an'].value_counts())
+print()
+display(df_4_tabs['last_char_clean_an'].value_counts())
+# is the `clean_account_number` a unique primary key? Or any duplicates?
+# look for non-unique account numbers using .groupby().transform()
+# https://pbpython.com/pandas_transform.html
+df_4_tabs['nuniq_acct_num'] = df_4_tabs.groupby('clean_account_number')['clean_account_number'].transform(len)
+df_4_tabs.query(" nuniq_acct_num>1 ")
+# look for account numbers (after cleaning) that are not length 6 characters
+df_4_tabs.query(" len_clean_acct_num !=6 ")
+Section 2:¶id column is numeric, but remaining columns convert to str (initially surprised account_number didn't convert numeric)id and email columns are completely unique, but the rest are not; even account_number has a few non-uniquesaccount_number: 114392account_number: 973758account_number column has length of 6 characters in 974 records, but remaining have different lengthsaccount_number by removing spaces, dashes, and slashes; two of the records are length 5 (consider leading zero that was removed?)account_number: 93128account_number: 75182account_number appear randomemail domains are almost unique, 904 uniques out of 994 rows
+# create list with anomalies '\t'
+ls_lines_anom_tab_delim = [x for x in ls_lines_tsv if x.count('\t') != 4]
+ls_lines_anom_tab_delim
+# create string with anomalies '\t'
+str_anom_tab_delim = ''.join(ls_lines_anom_tab_delim)
+str_anom_tab_delim
+# clean string: (a) replace newline with tab, (b) remove whitespaces, (c) replace double-tab with single-tab
+str_anom_tab_delim_clean = str_anom_tab_delim.replace('\n', '\t').replace(' ', '').replace('\t\t', '\t')
+str_anom_tab_delim_clean
+# examine string split on tab-delimeter
+str_anom_tab_delim_clean.split('\t')
+# convert list of text to str
+# # create str that joins all records: (a) replace newline with tab, (b) remove whitespaces, (c) replace double-tab with single-tab
+# str_tsv = ''.join(ls_lines_tsv).replace('\n', '\t').replace(' ', '').replace('\t\t', '\t')
+ls_clean_tsv = [x.replace('\n', '\t').replace(' ', '').replace('\t\t', '\t') for x in ls_lines_tsv]
+str_tsv = ''.join(ls_clean_tsv)
+
+# look for characters not letters or numbers
+print('Unique characters not numbers or letters:')
+print(set(re.findall('[^a-zA-Z0-9]', str_tsv)))
+print()
+
+# look for characters not letters or numbers ... in the raw utf-16-le string
+print('Unique characters not numbers or letters (utf-16-le):')
+print(set(re.findall('[^a-zA-Z0-9]', ''.join(ls_lines_tsv_utf16le))))
+print()
+# use regex groups to identify records
+# https://www.tutorialspoint.com/What-is-the-groups-method-in-regular-expressions-in-Python
+'''
+* id - one or more digits
+* name - may include 0, 1, 2, 3 names
+* account number - one or more digits that may contain '-' or '/'
+* email may contain one or more '@', '.'
+'''
+r_str_match_0names = '(\d+\\t[0-9-/]*\\t[a-zA-Z@.]*)'
+r_str_match_1names = '(\d+\\t[a-zA-Z]+\\t[0-9-/]*\\t[a-zA-Z@.]*)'
+r_str_match_2names = '(\d+\\t[a-zA-Z]+\\t[a-zA-Z]+\\t[0-9-/]*\\t[a-zA-Z@.]*)'
+r_str_match_3names = '(\d+\\t[a-zA-Z]+\\t[a-zA-Z]+\\t[a-zA-Z]+\\t[0-9-/]*\\t[a-zA-Z@.]*)'
+
+# create list of records
+ls_re_find_0names = re.findall(r_str_match_0names, str_anom_tab_delim_clean)
+ls_re_find_1names = re.findall(r_str_match_1names, str_anom_tab_delim_clean)
+ls_re_find_2names = re.findall(r_str_match_2names, str_anom_tab_delim_clean)
+ls_re_find_3names = re.findall(r_str_match_3names, str_anom_tab_delim_clean)
+
+print('Number of records with 0 names: ', len(ls_re_find_0names))
+print('Number of records with 1 names: ', len(ls_re_find_1names))
+print('Number of records with 2 names: ', len(ls_re_find_2names))
+print('Number of records with 3 names: ', len(ls_re_find_3names))
+print('Clean 3 names to 2 names: ')
+print(ls_re_find_3names)
+print()
+
+# clean 3 names by removing middle name
+for each_3name in ls_re_find_3names:
+
+ # convert to list, split on tab delimiter
+ temp_list = each_3name.split('\t')
+ print(temp_list)
+
+ # remove middle name
+ del temp_list[2]
+ print(temp_list)
+
+ print()
+# find id for any records that don't match 2 name pattern ...
+# ... this is how I discovered the accented characters
+ls_re_all_find_2names = re.findall(r_str_match_2names, str_tsv)
+ls_id_regex = [x.split('\t')[0] for x in ls_re_all_find_2names]
+for idx, item in enumerate(ls_id_regex):
+ if idx == len(ls_id_regex)-1:
+ print('End of List')
+ elif int(item)+1 != int(ls_id_regex[idx+1]):
+ print(item)
+Section 3:¶
+
+# create s3 resource
+s3_resource = boto3.resource('s3')
+
+# print available AWS S3 buckets
+# https://stackoverflow.com/questions/49372761/boto3-using-boto3-resources3-to-list-all-s3-buckets
+ls_buckets = [bucket.name for bucket in s3_resource.buckets.all()]
+for idx, each_bucket in enumerate(ls_buckets):
+ # print(idx, each_bucket)
+ pass
+# create redshift client
+rs_client = boto3.client('redshift')
+
+# print available redshift clusters
+# https://stackoverflow.com/questions/34309151/get-list-clusters-amazon-redshift-using-python-with-boto3
+# https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/redshift.html
+di_rs_clusters = rs_client.describe_clusters()
+print(di_rs_clusters['Clusters'])
+
+| \n", + " | id | \n", + "first_name | \n", + "last_name | \n", + "account_number | \n", + "|
|---|---|---|---|---|---|
| 0 | \n", + "1 | \n", + "Addison | \n", + "Marks | \n", + "196296 | \n", + "ornare.lectus@et.edu | \n", + "
| 1 | \n", + "2 | \n", + "Dakota | \n", + "Garza | \n", + "409025 | \n", + "scelerisque@Praesentluctus.edu | \n", + "
| 2 | \n", + "3 | \n", + "Basia | \n", + "Wolfe | \n", + "637720 | \n", + "Aliquam@nullaIntegerurna.com | \n", + "
| 3 | \n", + "4 | \n", + "Germaine | \n", + "Campbell | \n", + "826846 | \n", + "id.magna@viverraMaecenas.ca | \n", + "
| 4 | \n", + "5 | \n", + "Lenore | \n", + "Pennington | \n", + "345284 | \n", + "aliquam@Integer.edu | \n", + "
| \n", + " | id | \n", + "first_name | \n", + "last_name | \n", + "account_number | \n", + "|
|---|---|---|---|---|---|
| 298 | \n", + "302 | \n", + "NaN | \n", + "Copeland | \n", + "547803 | \n", + "Vivamus.non.lorem@sed.ca | \n", + "
| 439 | \n", + "444 | \n", + "Roary | \n", + "NaN | \n", + "607318 | \n", + "mi.pede@orci.ca | \n", + "
| 514 | \n", + "519 | \n", + "NaN | \n", + "Williamson | \n", + "231131 | \n", + "Nullam.nisl@massa.ca | \n", + "
| 533 | \n", + "538 | \n", + "jana | \n", + "NaN | \n", + "824675 | \n", + "nisi.dictum.augue@nonenimcommodo.co.uk | \n", + "
| 547 | \n", + "552 | \n", + "Fitzgerald | \n", + "NaN | \n", + "317355 | \n", + "elit.a@velit.co.uk | \n", + "
| 561 | \n", + "566 | \n", + "Whoopi | \n", + "NaN | \n", + "125742 | \n", + "feugiat.non.lobortis@enimSednulla.net | \n", + "
| 596 | \n", + "601 | \n", + "NaN | \n", + "Newton | \n", + "601770 | \n", + "Duis.ac@nuncinterdum.edu | \n", + "
| 608 | \n", + "613 | \n", + "NaN | \n", + "NaN | \n", + "104969 | \n", + "dictum@Suspendisse.net | \n", + "
| 624 | \n", + "629 | \n", + "NaN | \n", + "Riggs | \n", + "242923 | \n", + "nulla.ante.iaculis@erat.net | \n", + "
| 668 | \n", + "673 | \n", + "Vielka | \n", + "NaN | \n", + "270462 | \n", + "metus.Aenean@lectusNullamsuscipit.edu | \n", + "
| 753 | \n", + "758 | \n", + "NaN | \n", + "NaN | \n", + "155499 | \n", + "facilisis.facilisis@quamdignissimpharetra.net | \n", + "
| 766 | \n", + "771 | \n", + "NaN | \n", + "NaN | \n", + "935186 | \n", + "amet.consectetuer.adipiscing@purusgravida.net | \n", + "
| 804 | \n", + "810 | \n", + "NaN | \n", + "Bishop | \n", + "934203 | \n", + "Sed.et@at.net | \n", + "
| 842 | \n", + "848 | \n", + "NaN | \n", + "Hess | \n", + "340666 | \n", + "interdum.Nunc.sollicitudin@elementum.org | \n", + "
| 883 | \n", + "889 | \n", + "NaN | \n", + "Eaton | \n", + "292781 | \n", + "ac@idnunc.edu | \n", + "
| 972 | \n", + "978 | \n", + "NaN | \n", + "NaN | \n", + "958519 | \n", + "Aliquam.auctor.velit@fringillapurus.co.uk | \n", + "
| 980 | \n", + "987 | \n", + "NaN | \n", + "Burris | \n", + "233269 | \n", + "Sed.et@Proin.ca | \n", + "
| \n", + " | id | \n", + "first_name | \n", + "last_name | \n", + "account_number | \n", + "null_firstname | \n", + "null_lastname | \n", + "null_name | \n", + "len_acct_num | \n", + "domain_name | \n", + "|
|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "1 | \n", + "Addison | \n", + "Marks | \n", + "196296 | \n", + "ornare.lectus@et.edu | \n", + "False | \n", + "False | \n", + "False | \n", + "6 | \n", + "et.edu | \n", + "
| 1 | \n", + "2 | \n", + "Dakota | \n", + "Garza | \n", + "409025 | \n", + "scelerisque@Praesentluctus.edu | \n", + "False | \n", + "False | \n", + "False | \n", + "6 | \n", + "Praesentluctus.edu | \n", + "
| 2 | \n", + "3 | \n", + "Basia | \n", + "Wolfe | \n", + "637720 | \n", + "Aliquam@nullaIntegerurna.com | \n", + "False | \n", + "False | \n", + "False | \n", + "6 | \n", + "nullaIntegerurna.com | \n", + "
| 3 | \n", + "4 | \n", + "Germaine | \n", + "Campbell | \n", + "826846 | \n", + "id.magna@viverraMaecenas.ca | \n", + "False | \n", + "False | \n", + "False | \n", + "6 | \n", + "viverraMaecenas.ca | \n", + "
| 4 | \n", + "5 | \n", + "Lenore | \n", + "Pennington | \n", + "345284 | \n", + "aliquam@Integer.edu | \n", + "False | \n", + "False | \n", + "False | \n", + "6 | \n", + "Integer.edu | \n", + "
| \n", + " | id | \n", + "first_name | \n", + "last_name | \n", + "account_number | \n", + "null_firstname | \n", + "null_lastname | \n", + "null_name | \n", + "len_acct_num | \n", + "domain_name | \n", + "|
|---|---|---|---|---|---|---|---|---|---|---|
| 165 | \n", + "168 | \n", + "Nyssa | \n", + "Livingston | \n", + "897187 | \n", + "at@tortorat.net | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "tortorat.net | \n", + "
| 214 | \n", + "218 | \n", + "Ifeoma | \n", + "Whitney | \n", + "543699 | \n", + "Proin.nisl.sem@odiovelest.edu | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "odiovelest.edu | \n", + "
| 262 | \n", + "266 | \n", + "Howard | \n", + "Cooley | \n", + "167868 | \n", + "faucibus@ametultricies.org | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "ametultricies.org | \n", + "
| 272 | \n", + "276 | \n", + "Willa | \n", + "Diaz | \n", + "157615 | \n", + "Aliquam.tincidunt@metuseuerat.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "metuseuerat.co.uk | \n", + "
| 290 | \n", + "294 | \n", + "Wyoming | \n", + "Williams | \n", + "454-586 | \n", + "odio.a.purus@Suspendisse.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "Suspendisse.co.uk | \n", + "
| 295 | \n", + "299 | \n", + "Meghan | \n", + "Whitaker | \n", + "352355 | \n", + "leo@tempus.org | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "tempus.org | \n", + "
| 307 | \n", + "311 | \n", + "Kenneth | \n", + "Bird | \n", + "437/680 | \n", + "est@utpharetrased.org | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "utpharetrased.org | \n", + "
| 382 | \n", + "387 | \n", + "Palmer | \n", + "Acevedo | \n", + "168-722 | \n", + "ut.pellentesque.eget@eleifendCrassed.org | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "eleifendCrassed.org | \n", + "
| 411 | \n", + "416 | \n", + "elvis | \n", + "RIVERA | \n", + "865-008 | \n", + "Quisque.libero@vitaesodales.net | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "vitaesodales.net | \n", + "
| 471 | \n", + "476 | \n", + "Ivana | \n", + "Chapman | \n", + "357-130 | \n", + "et@Cras.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "Cras.co.uk | \n", + "
| 472 | \n", + "477 | \n", + "Hope | \n", + "Oneal | \n", + "893425 | \n", + "ut@ut.org | \n", + "False | \n", + "False | \n", + "False | \n", + "8 | \n", + "ut.org | \n", + "
| 489 | \n", + "494 | \n", + "Blaine | \n", + "Barker | \n", + "874570 | \n", + "elit.pretium@sociisnatoquepenatibus.net | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "sociisnatoquepenatibus.net | \n", + "
| 494 | \n", + "499 | \n", + "Kerry | \n", + "Howell | \n", + "730368 | \n", + "sed.consequat@ac.ca | \n", + "False | \n", + "False | \n", + "False | \n", + "9 | \n", + "ac.ca | \n", + "
| 567 | \n", + "572 | \n", + "Ginger | \n", + "Nelson | \n", + "475426 | \n", + "Duis.gravida.Praesent@vulputate.net | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "vulputate.net | \n", + "
| 620 | \n", + "625 | \n", + "Galena | \n", + "Holland | \n", + "460962 | \n", + "at.risus@tincidunt.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "8 | \n", + "tincidunt.co.uk | \n", + "
| 682 | \n", + "687 | \n", + "Fay | \n", + "Irwin | \n", + "1181-61 | \n", + "metus@elitsedconsequat.com | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "elitsedconsequat.com | \n", + "
| 830 | \n", + "836 | \n", + "Keegan | \n", + "McCoy | \n", + "93128 | \n", + "feugiat.nec@eu.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "5 | \n", + "eu.co.uk | \n", + "
| 954 | \n", + "960 | \n", + "Taylor | \n", + "Wallace | \n", + "75182 | \n", + "orci@dolor.net | \n", + "False | \n", + "False | \n", + "False | \n", + "5 | \n", + "dolor.net | \n", + "
| 966 | \n", + "972 | \n", + "Dorothy | \n", + "Roy | \n", + "734417 | \n", + "quis@Sedetlibero.ca | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "Sedetlibero.ca | \n", + "
| 976 | \n", + "982 | \n", + "Gemma | \n", + "Hartman | \n", + "137599 | \n", + "luctus@ProinmiAliquam.edu | \n", + "False | \n", + "False | \n", + "False | \n", + "12 | \n", + "ProinmiAliquam.edu | \n", + "
| \n", + " | id | \n", + "first_name | \n", + "last_name | \n", + "account_number | \n", + "null_firstname | \n", + "null_lastname | \n", + "null_name | \n", + "len_acct_num | \n", + "domain_name | \n", + "|
|---|---|---|---|---|---|---|---|---|---|---|
| 165 | \n", + "168 | \n", + "Nyssa | \n", + "Livingston | \n", + "897187 | \n", + "at@tortorat.net | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "tortorat.net | \n", + "
| 214 | \n", + "218 | \n", + "Ifeoma | \n", + "Whitney | \n", + "543699 | \n", + "Proin.nisl.sem@odiovelest.edu | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "odiovelest.edu | \n", + "
| 262 | \n", + "266 | \n", + "Howard | \n", + "Cooley | \n", + "167868 | \n", + "faucibus@ametultricies.org | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "ametultricies.org | \n", + "
| 272 | \n", + "276 | \n", + "Willa | \n", + "Diaz | \n", + "157615 | \n", + "Aliquam.tincidunt@metuseuerat.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "metuseuerat.co.uk | \n", + "
| 290 | \n", + "294 | \n", + "Wyoming | \n", + "Williams | \n", + "454-586 | \n", + "odio.a.purus@Suspendisse.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "Suspendisse.co.uk | \n", + "
| 295 | \n", + "299 | \n", + "Meghan | \n", + "Whitaker | \n", + "352355 | \n", + "leo@tempus.org | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "tempus.org | \n", + "
| 307 | \n", + "311 | \n", + "Kenneth | \n", + "Bird | \n", + "437/680 | \n", + "est@utpharetrased.org | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "utpharetrased.org | \n", + "
| 382 | \n", + "387 | \n", + "Palmer | \n", + "Acevedo | \n", + "168-722 | \n", + "ut.pellentesque.eget@eleifendCrassed.org | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "eleifendCrassed.org | \n", + "
| 411 | \n", + "416 | \n", + "elvis | \n", + "RIVERA | \n", + "865-008 | \n", + "Quisque.libero@vitaesodales.net | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "vitaesodales.net | \n", + "
| 471 | \n", + "476 | \n", + "Ivana | \n", + "Chapman | \n", + "357-130 | \n", + "et@Cras.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "Cras.co.uk | \n", + "
| 472 | \n", + "477 | \n", + "Hope | \n", + "Oneal | \n", + "893425 | \n", + "ut@ut.org | \n", + "False | \n", + "False | \n", + "False | \n", + "8 | \n", + "ut.org | \n", + "
| 489 | \n", + "494 | \n", + "Blaine | \n", + "Barker | \n", + "874570 | \n", + "elit.pretium@sociisnatoquepenatibus.net | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "sociisnatoquepenatibus.net | \n", + "
| 494 | \n", + "499 | \n", + "Kerry | \n", + "Howell | \n", + "730368 | \n", + "sed.consequat@ac.ca | \n", + "False | \n", + "False | \n", + "False | \n", + "9 | \n", + "ac.ca | \n", + "
| 567 | \n", + "572 | \n", + "Ginger | \n", + "Nelson | \n", + "475426 | \n", + "Duis.gravida.Praesent@vulputate.net | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "vulputate.net | \n", + "
| 620 | \n", + "625 | \n", + "Galena | \n", + "Holland | \n", + "460962 | \n", + "at.risus@tincidunt.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "8 | \n", + "tincidunt.co.uk | \n", + "
| 682 | \n", + "687 | \n", + "Fay | \n", + "Irwin | \n", + "1181-61 | \n", + "metus@elitsedconsequat.com | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "elitsedconsequat.com | \n", + "
| 966 | \n", + "972 | \n", + "Dorothy | \n", + "Roy | \n", + "734417 | \n", + "quis@Sedetlibero.ca | \n", + "False | \n", + "False | \n", + "False | \n", + "7 | \n", + "Sedetlibero.ca | \n", + "
| 976 | \n", + "982 | \n", + "Gemma | \n", + "Hartman | \n", + "137599 | \n", + "luctus@ProinmiAliquam.edu | \n", + "False | \n", + "False | \n", + "False | \n", + "12 | \n", + "ProinmiAliquam.edu | \n", + "
| \n", + " | id | \n", + "first_name | \n", + "last_name | \n", + "account_number | \n", + "null_firstname | \n", + "null_lastname | \n", + "null_name | \n", + "len_acct_num | \n", + "domain_name | \n", + "clean_account_number | \n", + "len_clean_acct_num | \n", + "first_char_clean_an | \n", + "last_char_clean_an | \n", + "nuniq_acct_num | \n", + "|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 410 | \n", + "415 | \n", + "Courtney | \n", + "Salinas | \n", + "114392 | \n", + "nec@nunc.net | \n", + "False | \n", + "False | \n", + "False | \n", + "6 | \n", + "nunc.net | \n", + "114392 | \n", + "6 | \n", + "1 | \n", + "2 | \n", + "2 | \n", + "
| 512 | \n", + "517 | \n", + "Wayne | \n", + "Wilson | \n", + "973758 | \n", + "nonummy@iaculis.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "6 | \n", + "iaculis.co.uk | \n", + "973758 | \n", + "6 | \n", + "9 | \n", + "8 | \n", + "2 | \n", + "
| 899 | \n", + "905 | \n", + "Alice | \n", + "Dyer | \n", + "973758 | \n", + "Vivamus.nibh.dolor@gravidamauris.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "6 | \n", + "gravidamauris.co.uk | \n", + "973758 | \n", + "6 | \n", + "9 | \n", + "8 | \n", + "2 | \n", + "
| 928 | \n", + "934 | \n", + "Nora | \n", + "Leonard | \n", + "114392 | \n", + "ornare.elit@libero.com | \n", + "False | \n", + "False | \n", + "False | \n", + "6 | \n", + "libero.com | \n", + "114392 | \n", + "6 | \n", + "1 | \n", + "2 | \n", + "2 | \n", + "
| \n", + " | id | \n", + "first_name | \n", + "last_name | \n", + "account_number | \n", + "null_firstname | \n", + "null_lastname | \n", + "null_name | \n", + "len_acct_num | \n", + "domain_name | \n", + "clean_account_number | \n", + "len_clean_acct_num | \n", + "first_char_clean_an | \n", + "last_char_clean_an | \n", + "nuniq_acct_num | \n", + "|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 830 | \n", + "836 | \n", + "Keegan | \n", + "McCoy | \n", + "93128 | \n", + "feugiat.nec@eu.co.uk | \n", + "False | \n", + "False | \n", + "False | \n", + "5 | \n", + "eu.co.uk | \n", + "93128 | \n", + "5 | \n", + "9 | \n", + "8 | \n", + "1 | \n", + "
| 954 | \n", + "960 | \n", + "Taylor | \n", + "Wallace | \n", + "75182 | \n", + "orci@dolor.net | \n", + "False | \n", + "False | \n", + "False | \n", + "5 | \n", + "dolor.net | \n", + "75182 | \n", + "5 | \n", + "7 | \n", + "2 | \n", + "1 | \n", + "