diff --git a/.gitignore b/.gitignore
index cb01194..c937fcd 100644
--- a/.gitignore
+++ b/.gitignore
@@ -15,4 +15,5 @@ experiment_code/lans/.Rhistory
 experiment_code/rq1/correlations/*
 .RData
 .Rhistory
-.config.json
\ No newline at end of file
+.config.json
+*pyc
\ No newline at end of file
diff --git a/experiment_code/1-popularity/overvie.py b/experiment_code/1-popularity/overvie.py
new file mode 100644
index 0000000..41650b4
--- /dev/null
+++ b/experiment_code/1-popularity/overvie.py
@@ -0,0 +1,181 @@
+
+# coding: utf-8
+import MySQLdb
+import json
+import time
+import random
+import urllib2
+import pandas as pd 
+
+with open("../.config.json") as fp:
+	config = json.load(fp)
+local_db_config = config["local_db"]
+conn = MySQLdb.connect(host=local_db_config["db_host"],user=local_db_config["db_user"], 
+									passwd=local_db_config["db_passwd"],db=local_db_config["db_name"],port=3306,charset='utf8mb4')
+cursor = conn.cursor()
+
+def profile_type(doc):
+	doc_id,repo_id,doc_location,doc_name,doc_type = doc
+	if doc_location.lower() in ["root",".github","docs"] and doc_type=="blob":
+		doc_name = doc_name.lower()
+		for fi in ["readme"]:
+			if doc_name.lower().find(fi) != -1:
+				return "readme"
+		for fi in ["license"]:
+			if doc_name.lower().find(fi) != -1:
+				return "license"
+		for fi in ["issue_template","pull_request_template"]:
+			if doc_name.lower().find(fi) != -1:
+				return "template"
+		for fi in ["code_of_conduct"]:
+			if doc_name.lower().find(fi) != -1:
+				return "COC"
+		for fi in ["contributing"]:
+			if doc_name.lower().find(fi) != -1:
+				return "contributing"
+		return None
+	elif doc_location.lower() in ["issue_template", "pull_request_template"] and doc_type=="blob":
+		return  "template"
+	else:
+		return None
+	return None
+
+
+def overview():
+	cursor.execute("select id from random_repos")
+	repos = set([item[0] for item in cursor.fetchall()])
+	prf_files = []
+	cursor.execute("select * from files")
+	files = cursor.fetchall()
+	for f in files:
+		if f[1] in repos:
+			prf_files.append([f[0],f[1],profile_type(f)])
+			# print f, profile_type(f)
+
+	repo_counts = len(repos)
+	dist = {"readme":set(),"license":set(),"template":set(),
+				"COC":set(),"contributing":set()}
+
+	for _f in prf_files:
+		doc_id,repo_id,doc_type = _f
+		if doc_type is not None:
+			dist[doc_type].add(repo_id)
+	for key, value in dist.items():
+		print key, "%.2f%%"%(len(value)*100.0/repo_counts)
+
+	cursor.execute("select count(id) from random_repos where description is not null")
+	print "desc", "%.2f%%"%(cursor.fetchone()[0]*100.0/repo_counts)
+
+def repo_profile(repo_id):
+	file_types = set()
+	cursor.execute("select * from files where repo_id=%s",(repo_id,))
+	files = cursor.fetchall()
+	for f in files:
+		f_t = profile_type(f)
+		if f_t is not None:
+			file_types.add(f_t)
+	return file_types
+
+def by_language():
+	cursor.execute("select id, language from random_repos")
+	repos = cursor.fetchall()
+	language_dist = {}
+
+	file_dist = {}
+
+	for item in repos:
+		repo_id, repo_lan = item
+		if repo_lan not in language_dist:
+			language_dist[repo_lan] = 0
+		language_dist[repo_lan] += 1
+		if repo_lan not in file_dist:
+				file_dist[repo_lan] = {}
+		repo_files = repo_profile(repo_id)
+		for rf in repo_files:
+			if rf not in file_dist[repo_lan]:
+				file_dist[repo_lan][rf] = 0
+			file_dist[repo_lan][rf] += 1
+	lans = sorted(language_dist.items(), key=lambda x: x[1], reverse=True)
+	print lans
+	for lan, lan_count in lans:
+		tmp_lan_dist = file_dist[lan]
+		percentages = []
+		for _k in [ "readme","license","contributing","COC","template"]:
+			if _k not in tmp_lan_dist:
+				percentages.append(0)
+			else:
+				percentages.append(tmp_lan_dist[_k])
+		p_str = "|".join(["%.2f%%"%(item*100.0/language_dist[lan]) for item in percentages])
+		print "|%s|%d|%s|"%(lan,language_dist[lan],p_str)
+
+def by_role():
+	cursor.execute("select id, owner_type from random_repos")
+	repos = cursor.fetchall()
+	role_type = {}
+
+	file_dist = {}
+
+	for item in repos:
+		repo_id, repo_lan = item
+		if repo_lan not in role_type:
+			role_type[repo_lan] = 0
+		role_type[repo_lan] += 1
+		if repo_lan not in file_dist:
+				file_dist[repo_lan] = {}
+		repo_files = repo_profile(repo_id)
+		for rf in repo_files:
+			if rf not in file_dist[repo_lan]:
+				file_dist[repo_lan][rf] = 0
+			file_dist[repo_lan][rf] += 1
+	lans = sorted(role_type.items(), key=lambda x: x[1], reverse=True)
+	print lans
+	for lan, lan_count in lans:
+		tmp_lan_dist = file_dist[lan]
+		percentages = []
+		for _k in [ "readme","license","contributing","COC","template"]:
+			if _k not in tmp_lan_dist:
+				percentages.append(0)
+			else:
+				percentages.append(tmp_lan_dist[_k])
+		p_str = "|".join(["%.2f%%"%(item*100.0/role_type[lan]) for item in percentages])
+		print "|%s|%d|%s|"%(lan,role_type[lan],p_str)	
+
+
+import time
+def _strtime2int(strtime):
+	return time.mktime(time.strptime(strtime, '%Y-%m-%dT%H:%M:%SZ'))
+
+
+def by_age():
+	cursor.execute("select id, created_at from random_repos")
+	repos = cursor.fetchall()
+	# 第一个是包含的，第二个是不包含的
+	file_dist = { "readme":[[],[]],"license":[[],[]],"contributing":[[],[]],"COC":[[],[]],"template":[[],[]]}
+
+	for item in repos:
+		repo_id, repo_create = item
+		repo_files = repo_profile(repo_id)
+		repo_age =  (_strtime2int("2020-07-18T00:00:00Z") - _strtime2int(repo_create))/(60*60*24)
+		for key in file_dist.keys():
+			if key in repo_files:
+				file_dist[key][0].append(repo_age)
+			else:
+				file_dist[key][1].append(repo_age)
+	for key, value in file_dist.items():
+		stats1 = pd.Series(value[0])
+		stats2 = pd.Series(value[1])
+		print key, "Yes", stats1.min(), stats1.mean(),stats1.median(),stats1.std(),stats1.max()
+		print key, "No", stats2.min(), stats2.mean(),stats2.median(),stats2.std(),stats2.max()
+		print "----"*10
+
+
+
+if __name__ == "__main__":
+
+	# overview()
+	# by_language()
+	# by_role()
+	by_age()
+
+
+
diff --git a/experiment_code/dataset/get_repo_files.py b/experiment_code/dataset/get_repo_files.py
index 70afebb..d44494b 100644
--- a/experiment_code/dataset/get_repo_files.py
+++ b/experiment_code/dataset/get_repo_files.py
@@ -103,7 +103,7 @@ def get_files(repo):
 			break
 
 def get_dir_files(repo_id):
-	cursor.execute("select full_name from random_repos where id=%s",(repo_id,))
+	cursor.execute("select full_name from random_repos_before_fitler where id=%s",(repo_id,))
 	repo_slug = cursor.fetchone()[0]
 
 	file_url = "https://api.github.com/repos/%s/git/trees/%s"
@@ -147,8 +147,13 @@ def get_dir_files(repo_id):
 			print files
 			print "***"*10
 			for f in files:
-				cursor.execute("insert into files(repo_id, location, name, type) values(%s,%s,%s,%s)",
+				cursor.execute("select id from files where repo_id=%s and location=%s and name=%s",(repo_id, f[0], f[1]))
+				tmp_r = cursor.fetchone()
+				if tmp_r is None:
+					cursor.execute("insert into files(repo_id, location, name, type) values(%s,%s,%s,%s)",
 								(repo_id, f[0], f[1], f[2]))
+				else:
+					print "already"
 			conn.commit()
 			break
 
diff --git a/idea.md b/idea.md
index 5bbfca3..8275978 100644
--- a/idea.md
+++ b/idea.md
@@ -30,6 +30,40 @@ min、25%、mean、median、75%、max
 - age
 
 ### 2.2 Identification of documentation
+GitHub official suggestions:
+
+#### code-fo-coduct
+- https://docs.github.com/en/github/building-a-strong-community/adding-a-code-of-conduct-to-your-project
+	- root directory， docs directory，.github directory
+	- In the file name field, type CODE_OF_CONDUCT.md.
+
+#### contributing
+- https://docs.github.com/en/github/building-a-strong-community/setting-guidelines-for-repository-contributors
+	- root, docs, .github
+	- Contributing guidelines filenames are not case sensitive, and can have an extension such as .md or .txt.
+
+#### template
+- https://docs.github.com/en/github/building-a-strong-community/about-issue-and-pull-request-templates
+	- You must create templates on the repository's default branch. Templates created in other branches are not available for collaborators to use.
+	- root directory, the docs folder, or the hidden .github directory
+- https://docs.github.com/en/github/building-a-strong-community/configuring-issue-templates-for-your-repository
+- https://docs.github.com/en/github/building-a-strong-community/creating-a-pull-request-template-for-your-repository
+	- - root, docs, .github 
+	- 可以创建template 模板，然后再在配置文件里设置使用哪个template
+
+#### readme
+- https://docs.github.com/en/github/creating-cloning-and-archiving-repositories/about-readmes#relative-links-and-image-paths-in-readme-files
+	- root, docs, .github 
+
+#### license
+- https://docs.github.com/en/github/building-a-strong-community/adding-a-license-to-a-repository
+	- LICENSE or LICENSE.md (with all caps)	
+
+- https://docs.github.com/en/github/creating-cloning-and-archiving-repositories/licensing-a-repository
+	- Most people place their license text in a file named LICENSE.txt (or LICENSE.md) in the root of the repository. Some projects include information about their license in their README. For example, a project's README may include a note saying "This project is licensed under the terms of the MIT license."
+- 现实情况是，即使使用copying、copyright等关键词GitHub也能关联起来
+
+#### *Summary*
 - location:
 According to GitHub's conventions, community profile documentations can be placed in three directories. i.e.,
 	- root 
@@ -45,9 +79,37 @@ According to GitHub's conventions, community profile documentations can be place
 #### RQ1. What is the frequency/popularity of community profile documentation?
 
 - Overview
+
+| Type | desc | readme | license| contributing | COC|template |
+|:-|:-|:-|:-|:-|:-|:-|
+|Percentage|100.00%|99.25%|82.05%|28.70%|11.15%|24.05%
+
+
 - by programing language
+
+| Language | Count | readme | license| contributing | COC|template |
+|:-|:-|:-|:-|:-|:-|:-|:-|
+JavaScript|386|99.74%|86.53%|30.31%|13.73%|22.28%|
+|Python|285|100.00%|84.56%|26.67%|8.07%|26.32%|
+|Java|179|99.44%|79.89%|25.14%|14.53%|27.93%|
+|C++|116|100.00%|76.72%|23.28%|6.90%|25.86%|
+|Go|116|100.00%|95.69%|43.10%|12.07%|32.76%|
+|PHP|111|97.30%|82.88%|36.94%|6.31%|28.83%|
+|TypeScript|88|100.00%|89.77%|**56.82%**|**18.18%**|**45.45%**|
+|C|83|100.00%|62.65%|24.10%|9.64%|20.48%|
+|Ruby|79|100.00%|83.54%|26.58%|8.86%|17.72%|
+|C#|71|100.00%|**98.59%**|28.17%|12.68%|25.35%|
+
 - by user role
+
+| OwerType | Count | readme | license| contributing | COC|template |
+|:-|:-|:-|:-|:-|:-|:-|:-|
+|User|1033|98.94%|76.86%|13.36%|5.61%|13.75%|
+|Organization|967|99.59%|87.59%|45.09%|17.06%|36.40%|
+
+
 - by age
+
 - by forks (comparison of boxplot)
 
 #### RQ2. How is community profile documentation maintained?