Creted seperated folder for plotting

GenderCounts.txt

@@ -0,0 +1,3 @@
+Male count: 57802
+Female count: 27042
+Not Classified: 62794

Queries.txt

@@ -41,4 +41,13 @@ SELECT userID, COUNT(DISTINCT assetURL) as ArticlesCount from comments group by
 
 
 how many sections different commenters show interest:
-SELECT C.userID, count(distinct section) as secCount from comments C, articles A where C.assetURL = A.webURL and section is not null group by C.userID order by secCount desc
+SELECT C.userID, count(distinct section) as secCount from comments C, articles A where C.assetURL = A.webURL and section is not null group by C.userID order by secCount desc
+
+No Of Articles commented on by male user:
+select C.userID, count(distinct C.assetURL) as artCount from comments C, commenterGender CG where C.userID = CG.userID and CG.gender =   'male' group by C.userID order by artCount desc;
+
+No Of Articles commented on by female user:
+select C.userID, count(distinct C.assetURL) as artCount from comments C, commenterGender CG where C.userID = CG.userID and CG.gender =   'female' group by C.userID order by artCount desc;
+
+--male Comments
+select t1.userID, t2.userName, t1.commentBody from comments t1, commenterGender t2 where t1.userID = t2.userID and t2.gender = 'male');

genderExtraction.py

@@ -2,7 +2,7 @@
 import sexmachine.detector as gender
 
 
-db = sqlite3.connect('../commentdata.db')
+db = sqlite3.connect('../commentsData.db')
 d = gender.Detector(case_sensitive=False)
 c = db.cursor()
 c.execute("create table if not exists commenterGender(userID int,username text,gender text,\

plot_gender_noOfArticles.py → plotting/plot_Commenters_NoOfArticles.py

@@ -5,7 +5,7 @@
 
 c = db.cursor()
 
-c.execute("select C.userID, count(distinct C.assetURL) as artCount from comments C, commenterGender CG where C.userID = CG.userID and CG.gender =   'female' group by C.userID order by artCount desc;")
+c.execute("SELECT userID, COUNT(DISTINCT assetURL) as ArticlesCount from comments group by userID order by ArticlesCount desc")
 
 print "queruy exec'ed"
 userids = []
@@ -21,8 +21,8 @@
 plt.plot(pos, articlesCount, marker = '.', linewidth = 0)
 #rect1 = plt.bar(pos, secCount, align= 'center')
 plt.ylabel('No of Articles')
-plt.xlabel('Female Commenters')
-plt.title('Articles Distribution over Female Commenters')
+plt.xlabel('Commenters')
+plt.title('Articles Distribution over Commenters')
 #plt.xticks(pos, userids)
 plt.xticks(rotation=0)
 

plotting/plot_gender_noOfArticles.py

@@ -0,0 +1,51 @@
+import sqlite3
+import matplotlib.pyplot as plt
+
+db = sqlite3.connect('../commentsData.db')
+
+c = db.cursor()
+
+c.execute("select C.userID, count(distinct C.assetURL) as artCount from comments C, commenterGender CG where C.userID = CG.userID and CG.gender =   'female' group by C.userID order by artCount desc;")
+
+print "queruy exec'ed"
+fuserids = []
+farticlesCount = []
+
+for t in c.fetchall():
+    fuserids.append(t[0])
+    farticlesCount.append(t[1])
+
+pos =  range(len(fuserids))
+print max(farticlesCount)
+
+plt.plot(pos, farticlesCount, marker = '.', linewidth = 0, color = 'red', label = 'Female')
+
+
+c.execute("select C.userID, count(distinct C.assetURL) as artCount from comments C, commenterGender CG where C.userID = CG.userID and CG.gender =   'male' group by C.userID order by artCount desc;")
+
+muserids = []
+marticlesCount = []
+
+for t in c.fetchall():
+    muserids.append(t[0])
+    marticlesCount.append(t[1])
+
+pos =  range(len(muserids))
+print max(marticlesCount)
+
+plt.plot(pos, marticlesCount, marker = '.', linewidth = 0, color = 'blue', label = 'Male')
+
+
+#rect1 = plt.bar(pos, secCount, align= 'center')
+plt.ylabel('No of Articles')
+plt.xlabel('Commenters')
+plt.legend()
+plt.title('Articles Distribution over Male and Female Commenters')
+#plt.xticks(pos, userids)
+plt.xticks(rotation=0)
+
+
+
+
+plt.show()
+#plt.savefig('commentsDistribution.png', bbox_inches='tight')

sectionDistribution.py → plotting/sectionDistribution.py

@@ -36,5 +36,5 @@ def autolabel(rects):
 autolabel(rect1)
 
 
-#plt.show()
-plt.savefig("SectionDistibution.png", bbox_inches='tight')
+plt.show()
+#plt.savefig("SectionDistibution.png", bbox_inches='tight')

queries.py

@@ -0,0 +1,40 @@
+import sqlite3
+import matplotlib.pyplot as plt
+
+db = sqlite3.connect('../commentsData.db')
+
+c = db.cursor()
+
+c.execute("select section, count(*) as 'Count' from ArticleSection GROUP BY section ORDER BY Count")
+
+sections = []
+secCount = []
+
+for t in c.fetchall():
+    sections.append(t[0])
+    secCount.append(t[1])
+
+
+
+pos =  range(len(sections))
+print max(secCount)
+
+rect1 = plt.bar(pos, secCount, align= 'center')
+plt.ylabel('No of Articles')
+plt.xlabel('Section Names')
+plt.title('Section Distribution over Articles')
+plt.xticks(pos, sections)
+plt.xticks(rotation=90)
+
+def autolabel(rects):
+    # attach some text labels
+    for rect in rects:
+        height = rect.get_height()
+        plt.text(rect.get_x()+rect.get_width()/2., 1.01*height, '%d'%int(height),
+                ha='center', va='bottom', rotation = 90)
+
+autolabel(rect1)
+
+
+plt.show()
+#plt.savefig("SectionDistibution.png", bbox_inches='tight')