Issue while filtering the data from a list
I have a large list and I am trying to create multiple data frames from the same. For that I'm filtering out data in various variables. Basic structure of most of code is same and all are working fine except for one.
This the list.
structure(list(X1 = c("CTRI Number", "Last Modified On:", "Post Graduate Thesis",
"Type of Trial", "Type of Study\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Study Design", "Public Title of Study", "Scientific Title of Study",
"Trial Acronym", "Secondary IDs if Any", "Secondary ID", "NIL",
"Details of Principal Investigator or overall Trial Coordinator (multi-center study)\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Name", "Designation", "Affiliation", "Address", "Phone", "Fax",
"Email", "Details of Contact PersonScientific Query\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Name", "Designation", "Affiliation", "Address", "Phone", "Fax",
"Email", "Details of Contact PersonPublic Query\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Name", "Designation", "Affiliation", "Address", "Phone", "Fax",
"Email", "Source of Monetary or Material Support\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Wellcome Microbiology Research Fund,\r\r\nChristian Medical College, Vellore",
"Primary Sponsor\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Name", "Address", "Type of Sponsor", "Details of Secondary Sponsor",
"Name", "NIL", "Countries of Recruitment", "Sites of Study\r\n \r\n \r\n \r\n \r\n Modification(s)",
"No of Sites = 1", "Name of Principal\r\nInvestigator", "Gagandeep Kang",
"Details of Ethics Committee", "No of Ethics Committees= 1",
"Name of Committee", "IRB; Christian Medical College, Vellore",
"Regulatory Clearance Status from DCGI", "Status", "Not Applicable",
"Health Condition / Problems Studied\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Health Type", "Patients", "Intervention / Comparator Agent\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Type", "Intervention", "Comparator Agent", "Inclusion Criteria\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Age From", "Age To", "Gender", "Details", "ExclusionCriteria",
"Details", "Method of Generating Random Sequence", "Method of Concealment",
"Blinding/Masking", "Primary Outcome\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Outcome", "Duration of diarrhoea (time to first formed stool)",
"Secondary Outcome", "Outcome", "1. Severity of diarrhoea \r\r\n2. Requirement for rehydration",
"Target Sample Size\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Phase of Trial", "Date of First Enrollment (India)\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Date of Study Completion (India)", "Date of First Enrollment (Global)",
"Date of Study Completion (Global)", "Estimated Duration of Trial",
"Recruitment Status of Trial (Global)\r\n \r\n \r\n \r\n \r\n Modification(s)",
"Recruitment Status of Trial (India)", "Publication Details",
"Individual Participant Data (IPD) Sharing Statement", "Brief Summary"
), X2 = c("CTRI/2007/091/000001 [Registered on: 29/08/2007]",
"04/08/2014", "No", "Interventional", "Drug", "Randomized, Parallel Group, Active Controlled Trial",
"A community based clinical trial to study the effects of Racecadotril and standard care versus standard care alone in children below 5 years of age with diarrhoea",
"Community-based randomized control trial of racecadotril in gastroenteritis in children less than 5 years of age",
"", "Secondary ID \r\n Identifier \r\n NIL \r\n NIL",
"Identifier", "NIL", "Name \r\n Gagandeep Kang \r\n Designation \r\n Professor \r\n Affiliation \r\n Christian Medical College \r\n Address \r\n Department of Gastrointestinal SciencesChristian Medical College,\r\r\nVellore VelloreTAMIL NADU632002India \r\n Phone \r\n 0416-2282052 \r\n Fax \r\n 0416-2282486 \r\n Email \r\n [email protected]",
"Gagandeep Kang", "Professor", "Christian Medical College", "Department of Gastrointestinal SciencesChristian Medical College,\r\r\nVellore VelloreTAMIL NADU632002India",
"0416-2282052", "0416-2282486", "[email protected]", "Name \r\n Gagandeep Kang \r\n Designation \r\n Professor of Microbiology \r\n Affiliation \r\n Christian Medical College \r\n Address \r\n Department of Gastrointestinal SciencesChristian Medical College\r\r\nVelloreVelloreTAMIL NADU632002India \r\n Phone \r\n 0416-2282052 \r\n Fax \r\n 0416-2282486 \r\n Email \r\n [email protected]",
"Gagandeep Kang", "Professor of Microbiology", "Christian Medical College",
"Department of Gastrointestinal SciencesChristian Medical College\r\r\nVelloreVelloreTAMIL NADU632002India",
"0416-2282052", "0416-2282486", "[email protected]", "Name \r\n Gagandeep Kang \r\n Designation \r\n Professor of Microbiology \r\n Affiliation \r\n Christian Medical College \r\n Address \r\n Department of Gastrointestinal SciencesChristian Medical College\r\r\nVelloreVelloreTAMIL NADU632002India \r\n Phone \r\n 0416-2282052 \r\n Fax \r\n 0416-2282486 \r\n Email \r\n [email protected]",
"Gagandeep Kang", "Professor of Microbiology", "Christian Medical College",
"Department of Gastrointestinal SciencesChristian Medical College\r\r\nVelloreVelloreTAMIL NADU632002India",
"0416-2282052", "0416-2282486", "[email protected]", "Wellcome Microbiology Research Fund,\r\r\nChristian Medical College, Vellore",
NA, "Name \r\n Christian Medical College Vellore \r\n Address \r\n Bagayam\r\r\nVellore\r\r\n632002\r\r\nTamil Nadu \r\n Type of Sponsor \r\n Private medical college",
"Christian Medical College Vellore", "Bagayam\r\r\nVellore\r\r\n632002\r\r\nTamil Nadu",
"Private medical college", "Name \r\n Address \r\n NIL",
"Address", "", "India", "No of Sites = 1 \r\n Name of Principal\r\nInvestigator \r\n Name of Site \r\n Site Address \r\n Phone/Fax/Email \r\n Gagandeep Kang \r\n Department of Gastroenterology \r\n Christian Medical College,Vellore 632002VelloreTAMIL NADU \r\n [email protected]",
"No of Sites = 1", "Name of Site", "Department of Gastroenterology",
"No of Ethics Committees= 1 \r\n Name of Committee \r\n Approval Status \r\n \r\n IRB; Christian Medical College, Vellore \r\n Approved",
"No of Ethics Committees= 1", "Approval Status", "Approved",
"Status \r\n \r\n Not Applicable",
NA, NA, "Health Type \r\n Condition \r\n Patients \r\n \t\tAcute gastroenteritis in children," ,
"Condition", "Acute gastroenteritis in children,", "Type \r\n Name \r\n Details \r\n Intervention \r\n Racecadotril oral \r\n 1.5 mg/kg for 3 days \r\n Comparator Agent \r\n Standard care \r\n Oral rehydration solution, etc., for 3 days",
"Name", "Racecadotril oral", "Standard care", "Age From \r\n 4.00 Month(s)\r\n Age To \r\n 59.00 Month(s)\r\n Gender \r\n Both \r\n Details \r\n Inclusion:Child 4-59 months, with acute watery diarrhoea <1 week duration,with three or more stools in a 24 hour period, not requiring intravenous rehydration, resident in Kasba/Ramanaickanpalayam, with parents willing for enrollment.",
"4.00 Month(s)", "59.00 Month(s)", "Both", "Inclusion:Child 4-59 months, with acute watery diarrhoea <1 week duration,with three or more stools in a 24 hour period, not requiring intravenous rehydration, resident in Kasba/Ramanaickanpalayam, with parents willing for enrollment.",
"Details \r\n Child <4 months or >60 months, not resident in Kasba/ Ramanaickanpalayam, bloody diarrhoea, diarrhoea requiring intravenous rehydration, diarrhoea >1 week duration, not willing for enrollment",
"Child <4 months or >60 months, not resident in Kasba/ Ramanaickanpalayam, bloody diarrhoea, diarrhoea requiring intravenous rehydration, diarrhoea >1 week duration, not willing for enrollment",
"Other", "Dates of Birth or day of the Week", "Open Label", "Outcome \r\n TimePoints \r\n Duration of diarrhoea (time to first formed stool) \r\n within first week or till time to first formed stool",
"TimePoints", "within first week or till time to first formed stool",
"Outcome \r\n TimePoints \r\n 1. Severity of diarrhoea \r\r\n2. Requirement for rehydration \r\n Days 1, 2 and 3 of follow-up",
"TimePoints", "Days 1, 2 and 3 of follow-up", "Total Sample Size=\"128\"Sample Size from India=\"128\" Final Enrollment numbers achieved (Total)= \"\" Final Enrollment numbers achieved (India)=\"\"",
"Phase 3", "30/06/2007", "Date Missing", "Date Missing", "Date Missing",
"Years=\"0\"Months=\"6\"Days=\"0\"", "Not Applicable", "Completed",
"", "Will individual participant data (IPD) be shared publicly (including data dictionaries)?",
"Racecadotril is an enkephalinase inhibitor that has been evaluated in only two randomized controlled trials in children. These studies showed that there was a significant reduction in stool output and duration, but since both studies were funded by the drug manufacturer, additional supporting data would be useful in evaluating the usefulness of this drug as an adjunct to oral rehydration therapy in the management of mild and moderate acute watery diarrhoea. In this study, we propose to randomize children attending an urban health clinic by days to receive or not receive racecadotril and follow them by daily home visits for 5 days to assess differences in duration of diarrhoea (time to first formed stool), severity and requirement for oral rehydration.\r\r\nThis study is aimed at evaluation the efficacy of racecadotril in the treatment of acute watery diarrhoea in children in the community. The objectives are\r\r\ni)\tto compare the duration of diarrhoea in children with diarrhoea receiving racecadotril in addition to oral rehydration and controls receiving oral rehydration alone,\r\r\nii)\tto compare the severity of diarrhoea in children receiving racecadotril in addition to oral rehydration and controls receiving oral rehydration alone,\r\r\niii)\tto compare the requirement for oral rehydration in children with diarrhoea receiving racecadotril in addition to oral rehydration and controls receiving oral rehydration alone,\r\r\niv)\tto compare differences in duration, severity and requirement for oral rehydration among racecadotril treated children with gastroenteritis associated with and not associated with rotavirus infection, and\r\r\nv)\tto document side-effects, if any, of racecadotril during treatment and for two days following therapy."
), X3 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, "Secondary ID",
NA, NA, "Name", NA, NA, NA, NA, NA, NA, NA, "Name", NA, NA, NA,
NA, NA, NA, NA, "Name", NA, NA, NA, NA, NA, NA, NA, "Wellcome Microbiology Research Fund,\r\r\nChristian Medical College, Vellore",
NA, "Name", NA, NA, NA, "Name", NA, NA, NA, "No of Sites = 1",
"No of Sites = 1", "Site Address", "Christian Medical College,Vellore 632002VelloreTAMIL NADU",
"No of Ethics Committees= 1", "No of Ethics Committees= 1", NA,
NA, "Status", NA, NA, "Health Type", NA, NA, "Type", "Details",
"1.5 mg/kg for 3 days", "Oral rehydration solution, etc., for 3 days",
"Age From", NA, NA, NA, NA, "Details", NA, NA, NA, NA, "Outcome",
NA, NA, "Outcome", NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA), X4 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, "Identifier",
NA, NA, "Gagandeep Kang", NA, NA, NA, NA, NA, NA, NA, "Gagandeep Kang",
NA, NA, NA, NA, NA, NA, NA, "Gagandeep Kang", NA, NA, NA, NA,
NA, NA, NA, NA, NA, "Christian Medical College Vellore", NA,
NA, NA, "Address", NA, NA, NA, "No of Sites = 1", "No of Sites = 1",
"Phone/Fax/Email", "[email protected]",
"No of Ethics Committees= 1", "No of Ethics Committees= 1", NA,
NA, "Not Applicable", NA, NA, "Condition", NA, NA, "Name", NA,
NA, NA, "4.00 Month(s)", NA, NA, NA, NA, "Child <4 months or >60 months, not resident in Kasba/ Ramanaickanpalayam, bloody diarrhoea, diarrhoea requiring intravenous rehydration, diarrhoea >1 week duration, not willing for enrollment",
NA, NA, NA, NA, "TimePoints", NA, NA, "TimePoints", NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), X5 = c(NA, NA, NA,
NA, NA, NA, NA, NA, NA, "NIL", NA, NA, "Designation", NA, NA,
NA, NA, NA, NA, NA, "Designation", NA, NA, NA, NA, NA, NA, NA,
"Designation", NA, NA, NA, NA, NA, NA, NA, NA, NA, "Address",
NA, NA, NA, "NIL", NA, NA, NA, "No of Sites = 1", NA, NA, NA,
"No of Ethics Committees= 1", "No of Ethics Committees= 1", NA,
NA, NA, NA, NA, "Patients", NA, NA, "Details", NA, NA, NA, "Age To",
NA, NA, NA, NA, NA, NA, NA, NA, NA, "Duration of diarrhoea (time to first formed stool)",
NA, NA, "1. Severity of diarrhoea \r\r\n2. Requirement for rehydration",
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), X6 = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, "NIL", NA, NA, "Professor", NA,
NA, NA, NA, NA, NA, NA, "Professor of Microbiology", NA, NA,
NA, NA, NA, NA, NA, "Professor of Microbiology", NA, NA, NA,
NA, NA, NA, NA, NA, NA, "Bagayam\r\r\nVellore\r\r\n632002\r\r\nTamil Nadu",
NA, NA, NA, "", NA, NA, NA, "No of Sites = 1", NA, NA, NA, "No of Ethics Committees= 1",
NA, NA, NA, NA, NA, NA, "Acute gastroenteritis in children,",
NA, NA, "Intervention", NA, NA, NA, "59.00 Month(s)", NA, NA,
NA, NA, NA, NA, NA, NA, NA, "within first week or till time to first formed stool",
NA, NA, "Days 1, 2 and 3 of follow-up", NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA), X7 = c(NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, "Affiliation", NA, NA, NA, NA, NA, NA,
NA, "Affiliation", NA, NA, NA, NA, NA, NA, NA, "Affiliation",
NA, NA, NA, NA, NA, NA, NA, NA, NA, "Type of Sponsor", NA, NA,
NA, NA, NA, NA, NA, "Name of Principal\r\nInvestigator", NA,
NA, NA, "No of Ethics Committees= 1", NA, NA, NA, NA, NA, NA,
NA, NA, NA, "Racecadotril oral", NA, NA, NA, "Gender", NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA), X8 = c(NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, "Christian Medical College", NA,
NA, NA, NA, NA, NA, NA, "Christian Medical College", NA, NA,
NA, NA, NA, NA, NA, "Christian Medical College", NA, NA, NA,
NA, NA, NA, NA, NA, NA, "Private medical college", NA, NA, NA,
NA, NA, NA, NA, "Name of Site", NA, NA, NA, "Name of Committee",
NA, NA, NA, NA, NA, NA, NA, NA, NA, "1.5 mg/kg for 3 days", NA,
NA, NA, "Both", NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA),
X9 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "Address",
NA, NA, NA, NA, NA, NA, NA, "Address", NA, NA, NA, NA, NA,
NA, NA, "Address", NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, "Site Address", NA, NA, NA, "Approval Status",
NA, NA, NA, NA, NA, NA, NA, NA, NA, "Comparator Agent", NA,
NA, NA, "Details", NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA), X10 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, "Department of Gastrointestinal SciencesChristian Medical College,\r\r\nVellore VelloreTAMIL NADU632002India",
NA, NA, NA, NA, NA, NA, NA, "Department of Gastrointestinal SciencesChristian Medical College\r\r\nVelloreVelloreTAMIL NADU632002India",
NA, NA, NA, NA, NA, NA, NA, "Department of Gastrointestinal SciencesChristian Medical College\r\r\nVelloreVelloreTAMIL NADU632002India",
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, "Phone/Fax/Email", NA, NA, NA, "IRB; Christian Medical College, Vellore",
NA, NA, NA, NA, NA, NA, NA, NA, NA, "Standard care", NA,
NA, NA, "Inclusion:Child 4-59 months, with acute watery diarrhoea <1 week duration,with three or more stools in a 24 hour period, not requiring intravenous rehydration, resident in Kasba/Ramanaickanpalayam, with parents willing for enrollment.",
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), X11 = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "Phone", NA,
NA, NA, NA, NA, NA, NA, "Phone", NA, NA, NA, NA, NA, NA,
NA, "Phone", NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, "Gagandeep Kang", NA, NA, NA, "Approved",
NA, NA, NA, NA, NA, NA, NA, NA, NA, "Oral rehydration solution, etc., for 3 days",
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA), X12 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, "0416-2282052", NA, NA, NA, NA, NA, NA, NA, "0416-2282052",
NA, NA, NA, NA, NA, NA, NA, "0416-2282052", NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "Department of Gastroenterology",
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA
), X13 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
"Fax", NA, NA, NA, NA, NA, NA, NA, "Fax", NA, NA, NA, NA,
NA, NA, NA, "Fax", NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, "Christian Medical College,Vellore 632002VelloreTAMIL NADU",
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA
), X14 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
"0416-2282486", NA, NA, NA, NA, NA, NA, NA, "0416-2282486",
NA, NA, NA, NA, NA, NA, NA, "0416-2282486", NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "[email protected]",
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA
), X15 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
"Email", NA, NA, NA, NA, NA, NA, NA, "Email", NA, NA, NA,
NA, NA, NA, NA, "Email", NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), X16 = c(NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "[email protected]",
NA, NA, NA, NA, NA, NA, NA, "[email protected]", NA,
NA, NA, NA, NA, NA, NA, "[email protected]", NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA)), row.names = c(NA, -92L), class = c("tbl_df", "tbl",
"data.frame"))
And I'm trying to filter out some details using below code.
Code1: (Works perfectly fine)
commonTable$Last_modified_on = as.character(webpage %>%
filter(X1 %like% "Last Modified On") %>%
select(X2))
Code2: (Runs fine but no output)
commonTable$Date_first_enrol_India = as.character(webpage %>%
filter(X1 %like% "Date of First Enrollment (India)") %>%
select(X2))
What am I missing here?
In a regular expression parentheses are special characters which are used for grouping. Hence, if you want to search for a string containing parentheses you have to escape them using \\( and \\):
library(dplyr)
library(data.table)
as.character(webpage %>%
filter(X1 %like% "Date of First Enrollment \\(India\\)") %>%
select(X2))
#> [1] "30/06/2007"
Created on 2022-01-20 by the reprex package (v2.0.1)