Libraries

library('knitr')
library('markdown')
library('tidyr')
library('RCurl')
library('plyr')
library('dplyr')
library('ggplot2')

Sources

https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.03.2016.csv

https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.04.2016.csv

https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.05.2016.csv

https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.06.2016.csv

https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.07.2016.csv

https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.08.2016.csv

https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.09.2016.csv

2016-05-03

Import CSV

x503 <- getURL("https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.03.2016.csv") #import twitter CSV

tweets503<- data.frame(read.csv(text=x503, header=T)) #create data frame

kable(head(tweets503,3)) #show head

X	tweet	city	movie	day	Sentiment_Score
1	@iTIGERSHROFF. Just saw Baaghi movie..Its unique good action movie. Not like other bollywood movie hide and seek behind tree.	Boston	Baaghi	05.03.2016	0.9355539
2	BOLLYWOOD: Movie Review: Tigers mean moves apart, Baaghi is a dud https://t.co/LNEnYFtXto	Boston	Baaghi	05.03.2016	0.0168295
3	Review: Baaghi, a Bollywood Rebel Tale in Search of a Cause: Fists and feet fly in this movie with… https://t.co/Gv5t0tcbZr NY Times	New York City	Baaghi	05.03.2016	0.6880249

dim(tweets503)

## [1] 2440    6

Movie Score

moviesum503<- ddply(tweets503, .(movie), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by movie
      
kable(moviesum503)

movie	Sentiment_Score	Count_of_Tweets
A Beautiful Planet	0.6871244	83
Baaghi	0.5751260	25
Dough	0.5094406	20
Eva Hesse	0.7894652	3
Green Room	0.6758744	161
Hockney	0.5284491	3
Keanu	0.6652038	1077
LAttesa (The Wait)	0.7607310	3
Men & Chicken	0.6032591	8
Mothers Day	0.6506948	362
Older Than Ireland	0.4218353	3
Pali Road	0.4949967	2
Papa: Hemingway in Cuba	0.6049819	29
Ratchet & Clank	0.6295204	482
Sacrifice	0.7101497	21
The American Side	0.7633015	2
The Family Fang	0.7413473	33
The Man Who Knew Infinity	0.8379256	31
The Meddler	0.6316935	51
Transfixed	0.8723244	1
Viktoria	0.5664273	3
Viva	0.6682436	37

Movie and City Score

moviecitysum503<- ddply(tweets503, .(movie, city), summarize,  Sentiment_Score=mean(Sentiment_Score)) #summarize by movie and city
      
kable(moviecitysum503)

City Score

citysum503<- ddply(tweets503, .(city), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by city
      
kable(citysum503)

city	Sentiment_Score	Count_of_Tweets
Boston	0.6418038	102
Chicago	0.6047630	242
Denver	0.6624649	87
Houston	0.6742386	96
Lincoln	0.8345247	3
los Angeles	0.6403698	797
New Orleans	0.6383094	86
New York City	0.6789346	855
Seattle	0.6545303	104
St. Louis	0.7729804	68

Unique Movies

allmovies503<-unique(tweets503[c("movie")]) # get unique movies
allmovies503$num<-seq.int(nrow(allmovies503)) # add counter row
kable(allmovies503) #show unique values for movie name

	movie	num
1	Baaghi	1
26	Keanu	2
1103	The American Side	3
1105	Pali Road	4
1107	Papa: Hemingway in Cuba	5
1136	Dough	6
1156	The Family Fang	7
1189	The Man Who Knew Infinity	8
1220	Viva	9
1257	Mothers Day	10
1619	LAttesa (The Wait)	11
1622	Older Than Ireland	12
1625	A Beautiful Planet	13
1708	Ratchet & Clank	14
2190	Viktoria	15
2193	Transfixed	16
2194	Sacrifice	17
2215	Eva Hesse	18
2218	Men & Chicken	19
2226	Hockney	20
2229	The Meddler	21
2280	Green Room	22

Graphs

ggplot(
  moviesum503, aes(x = reorder(movie,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("Movie Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="Movies",y="Score")

ggplot(
  citysum503, aes(x = reorder(city,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("City Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="City",y="Score")

2016-05-04

Import CSV

x504 <- getURL("https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.04.2016.csv") #import twitter CSV

tweets504<- data.frame(read.csv(text=x504, header=T)) #create data frame

kable(head(tweets504,3)) #show head

X	tweet	city	movie	day	Sentiment_Score
1	RT @PeteBlackburn: Somehow Keanu, a movie about fake gangsters trying to rescue a kitten, was stupider than I expected	Boston	Keanu	05.04.2016	0.0813694
2	Somehow Keanu, a movie about fake gangsters trying to rescue a kitten, was stupider than I expected	Boston	Keanu	05.04.2016	0.0937185
3	Keanu = Not Your Average Buddy Action Film: The AHH movie review of “Keanu” starring Keegan-Michael Key, Jo… https://t.co/SYtkk6Q98L	New York City	Keanu	05.04.2016	0.7579466

#dim(tweets504)

Movie Score

moviesum504<- ddply(tweets504, .(movie), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by movie
kable(moviesum504)

movie	Sentiment_Score	Count_of_Tweets
A Beautiful Planet	0.9350566	1
Green Room	0.6911169	26
Keanu	0.7724452	69
Men & Chicken	0.8554496	1
Mothers Day	0.7642735	41
Older Than Ireland	0.3211677	1
Papa: Hemingway in Cuba	0.4434618	6
Ratchet & Clank	0.6825581	23
Sacrifice	0.6979232	2
The Family Fang	0.8095837	1
The Man Who Knew Infinity	0.9880090	1
The Meddler	0.6949428	6
Viktoria	0.3375587	1
Viva	0.5055177	5

Movie and City Score

moviecitysum504<- ddply(tweets504, .(movie, city), summarize,  Sentiment_Score=mean(Sentiment_Score)) #summarize by movie and city
kable(moviecitysum504)

City Score

citysum504<- ddply(tweets504, .(city), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by city
kable(citysum504)

city	Sentiment_Score	Count_of_Tweets
Boston	0.2904943	6
Chicago	0.6850258	13
Denver	0.7473017	11
Houston	0.7808763	7
Los Angeles	0.6956255	53
New Orleans	0.6497442	2
New York City	0.7706122	81
Seattle	0.3175780	2
St. Louis	0.8605957	9

Unique Movies

allmovies504<-unique(tweets504[c("movie")]) # get unique movies
allmovies504$num<-seq.int(nrow(allmovies504)) # add counter row
kable(allmovies504) #show unique values for movie name

	movie	num
1	Keanu	1
70	Papa: Hemingway in Cuba	2
76	The Family Fang	3
77	The Man Who Knew Infinity	4
78	Viva	5
83	Mothers Day	6
124	Older Than Ireland	7
125	A Beautiful Planet	8
126	Ratchet & Clank	9
149	Viktoria	10
150	Sacrifice	11
152	Men & Chicken	12
153	The Meddler	13
159	Green Room	14

Graphs

ggplot(
  moviesum504, aes(x = reorder(movie,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("Movie Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="Movies",y="Score")

ggplot(
  citysum504, aes(x = reorder(city,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("City Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="City",y="Score")

2016-05-05

Import CSV

x505 <- getURL("https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.05.2016.csv") #import twitter CSV

tweets505<- data.frame(read.csv(text=x505, header=T)) #create data frame

kable(head(tweets505,3)) #show head

X	tweet	city	movie	day	Sentiment_Score
1	Movie Review: Keanu https://t.co/0GCZyi7rdy https://t.co/O6HjwlBaA5	Boston	Keanu	05.05.2016	0.9367028
2	RT @PeteBlackburn: Somehow Keanu, a movie about fake gangsters trying to rescue a kitten, was stupider than I expected	Boston	Keanu	05.05.2016	0.0813694
3	RT @Tribeca: Key and Peele’s subversive intelligence powers the comedy duo’s gleefully-absurd #KEANU. https://t.co/EKnyjGUklc https://t.co/	New York City	Keanu	05.05.2016	0.3208861

#dim(tweets505)

Movie Score

moviesum505<- ddply(tweets505, .(movie), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by movie
kable(moviesum505)

movie	Sentiment_Score	Count_of_Tweets
A Beautiful Planet	0.9702582	6
Dough	0.6558193	1
Eva Hesse	0.9344939	1
Green Room	0.6873747	20
Keanu	0.5245778	33
Men & Chicken	0.8554496	1
Mothers Day	0.7285004	30
Ratchet & Clank	0.6738906	14
Sacrifice	0.7061121	2
The Family Fang	0.8059055	7
The Man Who Knew Infinity	0.9051434	2
The Meddler	0.8200938	4
Viva	0.7874603	3

Movie and City Score

moviecitysum505<- ddply(tweets505, .(movie, city), summarize,  Sentiment_Score=mean(Sentiment_Score)) #summarize by movie and city
kable(moviecitysum505)

City Score

citysum505<- ddply(tweets505, .(city), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by city
kable(citysum505)

city	Sentiment_Score	Count_of_Tweets
Boston	0.5593184	7
Chicago	0.7237302	14
Denver	0.8007684	1
Houston	0.8031522	10
Los Angeles	0.6393636	41
New Orleans	0.3105057	1
New York City	0.6979320	42
Seattle	0.8005825	8

Unique Movies

allmovies505<-unique(tweets505[c("movie")]) # get unique movies
allmovies505$num<-seq.int(nrow(allmovies505)) # add counter row
kable(allmovies505) #show unique values for movie name

	movie	num
1	Keanu	1
34	Dough	2
35	The Family Fang	3
42	The Man Who Knew Infinity	4
44	Viva	5
47	Mothers Day	6
77	A Beautiful Planet	7
83	Ratchet & Clank	8
97	Sacrifice	9
99	Eva Hesse	10
100	Men & Chicken	11
101	The Meddler	12
105	Green Room	13

Graphs

ggplot(
  moviesum505, aes(x = reorder(movie,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("Movie Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="Movies",y="Score")

ggplot(
  citysum505, aes(x = reorder(city,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("City Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="City",y="Score")

2016-05-06

Import CSV

x506 <- getURL("https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.06.2016.csv") #import twitter CSV
tweets506<- data.frame(read.csv(text=x506, header=T)) #create data frame
kable(head(tweets506,3)) #show head

X	tweet	city	movie	day	Sentiment_Score
1	I gotta write something on Tiger. When I came out of #Baaghi I knew movie would do well&his star power would grow. Why everyone surprised??	New York City	Baaghi	05.06.2016	0.5727997
2	WATCH BAAGHI 2016 MOVIE ONLINE FORFREE https://t.co/6xOPr0jH39	Seattle	Baaghi	05.06.2016	0.2353356
3	@WahooFX Been checking out Key and Peele after seeing their movie, Keanu. Very clever writing. Funny guys.	New York City	Keanu	05.06.2016	0.8883232

#dim(tweets506)

Movie Score

moviesum506<- ddply(tweets506, .(movie), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by movie
kable(moviesum506)

movie	Sentiment_Score	Count_of_Tweets
A Beautiful Planet	0.9057405	2
Baaghi	0.4040677	2
Dough	0.5768954	1
Green Room	0.6289183	12
Keanu	0.7635731	43
Men & Chicken	0.8929113	1
Mothers Day	0.7848442	38
Older Than Ireland	0.2630552	1
Ratchet & Clank	0.6356453	14
The Family Fang	0.4418001	1
The Man Who Knew Infinity	0.9159938	1
The Meddler	0.3039157	7
Viktoria	0.4310602	1
Viva	0.4730699	1

Movie and City Score

moviecitysum506<- ddply(tweets506, .(movie, city), summarize,  Sentiment_Score=mean(Sentiment_Score)) #summarize by movie and city
kable(moviecitysum506)

City Score

citysum506<- ddply(tweets506, .(city), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by city
kable(citysum506)

city	Sentiment_Score	Count_of_Tweets
Boston	0.6107696	2
Chicago	0.7487589	9
Denver	0.7819757	4
Houston	0.6600502	8
Lincoln	0.0756081	1
Los Angeles	0.6522764	46
New Orleans	0.7454275	3
New York City	0.7753619	46
Seattle	0.5683229	5
St. Louis	0.6520504	1

Unique Movies

allmovies506<-unique(tweets506[c("movie")]) # get unique movies
allmovies506$num<-seq.int(nrow(allmovies506)) # add counter row
kable(allmovies506) #show unique values for movie name

	movie	num
1	Baaghi	1
3	Keanu	2
46	Dough	3
47	The Family Fang	4
48	The Man Who Knew Infinity	5
49	Viva	6
50	Mothers Day	7
88	Older Than Ireland	8
89	A Beautiful Planet	9
91	Ratchet & Clank	10
105	Viktoria	11
106	Men & Chicken	12
107	The Meddler	13
114	Green Room	14

Graphs

ggplot(
  moviesum506, aes(x = reorder(movie,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("Movie Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="Movies",y="Score")

ggplot(
  citysum506, aes(x = reorder(city,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("City Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="City",y="Score")

2016-05-07

Import CSV

x507 <- getURL("https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.07.2016.csv") #import twitter CSV
tweets507<- data.frame(read.csv(text=x507, header=T)) #create data frame
kable(head(tweets507,3)) #show head

X	tweet	city	movie	day	Sentiment_Score
1	RT @ScreenMediaFilm: Head to @FandangoNOW and rent or buy #MothersAndDaughters, a perfect #MothersDay gift - https://t.co/DP9dXEoqnq https:	New York City	Mothers and Daughters	05.07.2016	0.6272798
2	RT @ScreenMediaFilm: Right now! You can see a star-studded cast in #MothersAndDaughters on @iTunesMovies and in theaters! https://t.co/ExHC	New York City	Mothers and Daughters	05.07.2016	0.3594603
3	RT @ScreenMediaFilm: #MothersAndDaughters w/ @sharonstone @SusanSarandon@CourteneyCox @ChristinaRicci & more! https://t.co/ExHCyXv4CO http	New York City	Mothers and Daughters	05.07.2016	0.6668710

#dim(tweets507)

Movie Score

moviesum507<- ddply(tweets507, .(movie), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by movie
kable(moviesum507)

movie	Sentiment_Score	Count_of_Tweets
A Bigger Splash	0.5600869	27
A Hologram for the King	0.5971608	2
Baaghi	0.8501134	2
Being Charlie	0.6279919	12
Captain America: Civil War	0.7918589	661
Dark Horse	0.6029846	15
Dough	0.5761869	2
Elstree 1976	0.7597740	13
Elvis & Nixon	0.9997645	1
Green Room	0.5129880	6
Keanu	0.7290294	91
Men & Chicken	0.9700285	1
Mother’s Day	0.7051047	60
Mothers Day	0.7051047	60
Mothers and Daughters	0.7088384	17
Nina	0.6235115	9
Papa: Hemingway in Cuba	0.3656186	3
Ratchet & Clank	0.4689717	17
Sin Alas	0.2390684	1
The Family Fang	0.6779906	7
The Man Who Knew Infinity	0.9392011	4
The Meddler	0.4545197	6
The Offering	0.5217223	4
Those People	0.2774711	2
Viva	0.8058549	8

Movie and City Score

moviecitysum507<- ddply(tweets507, .(movie, city), summarize,  Sentiment_Score=mean(Sentiment_Score)) #summarize by movie and city
kable(moviecitysum507)

City Score

citysum507<- ddply(tweets507, .(city), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by city
kable(citysum507)

city	Sentiment_Score	Count_of_Tweets
Boston	0.7584916	39
Chicago	0.7521585	100
Denver	0.8490543	28
Houston	0.8431351	64
Lincoln	0.7778615	4
Los Angeles	0.7291199	304
New Orleans	0.9677572	2
New York City	0.7293779	419
Seattle	0.7912599	41
St. Louis	0.8351642	30

Unique Movies

allmovies507<-unique(tweets507[c("movie")]) # get unique movies
allmovies507$num<-seq.int(nrow(allmovies507)) # add counter row
kable(allmovies507) #show unique values for movie name

	movie	num
1	Mothers and Daughters	1
18	Elstree 1976	2
31	Those People	3
33	Being Charlie	4
45	The Offering	5
49	Dark Horse	6
64	Captain America: Civil War	7
725	A Bigger Splash	8
752	Baaghi	9
754	The Family Fang	10
761	The Man Who Knew Infinity	11
765	Dough	12
767	Mothers Day	13
827	Papa: Hemingway in Cuba	14
830	Ratchet & Clank	15
847	Viva	16
855	Keanu	17
946	Men & Chicken	18
947	Nina	19
956	Elvis & Nixon	20
957	A Hologram for the King	21
959	The Meddler	22
965	Green Room	23
971	Sin Alas	24
972	Mother’s Day	25

Graphs

ggplot(
  moviesum507, aes(x = reorder(movie,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("Movie Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="Movies",y="Score")

ggplot(
  citysum507, aes(x = reorder(city,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("City Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="City",y="Score")

2016-05-08

Import CSV

x508 <- getURL("https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.08.2016.csv") #import twitter CSV
tweets508<- data.frame(read.csv(text=x508, header=T)) #create data frame
kable(head(tweets508,3)) #show head

X	tweet	city	movie	day	Sentiment_Score
1	RT @ScreenMediaFilm: We’re about to crack the top #25 overall on @iTunesMovies - Help #MothersAndDaughters climb to #1 for Mother’s Day! ht	New York City	Mothers and Daughters	05.08.2016	0.2088123
2	RT @ScreenMediaFilm: Want a movie that’s PERFECT for this weekend? Go see #MothersAndDaughters right now in theaters, or on demand https://	New York City	Mothers and Daughters	05.08.2016	0.9672440
3	RT @ashanti: Had a blast with these lovely ladies at the premier for our movie “Mothers and daughters” last https://t.co/O78xXq7CHY	New York City	Mothers and Daughters	05.08.2016	0.9560200

#dim(tweets508)

Movie Score

moviesum508<- ddply(tweets508, .(movie), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by movie
kable(moviesum508)

movie	Sentiment_Score	Count_of_Tweets
A Beautiful Planet	0.9350566	1
A Bigger Splash	0.5229955	13
Baaghi	0.7681713	2
Being Charlie	0.6543891	4
Captain America: Civil War	0.7709729	506
Dark Horse	0.8021627	9
Dough	0.6988977	1
Elstree 1976	0.7146252	1
Elvis & Nixon	0.4100779	2
Green Room	0.6480975	13
Keanu	0.6793276	31
Mother’s Day	0.7164618	55
Mothers Day	0.7164618	55
Mothers and Daughters	0.6826797	20
Nina	0.7713823	3
Papa: Hemingway in Cuba	0.9939506	1
Ratchet & Clank	0.4775937	18
Sin Alas	0.3109672	1
The Family Fang	0.3585073	1
The Man Who Knew Infinity	0.8913501	2
The Meddler	0.7348663	6
The Offering	0.3625898	2
Those People	0.2172879	2
Viva	0.0386368	1

Movie and City Score

moviecitysum508<- ddply(tweets508, .(movie, city), summarize,  Sentiment_Score=mean(Sentiment_Score)) #summarize by movie and city
kable(moviecitysum508)

City Score

citysum508<- ddply(tweets508, .(city), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by city
kable(citysum508)

city	Sentiment_Score	Count_of_Tweets
Boston	0.7890522	22
Chicago	0.8017514	81
Denver	0.7297705	13
Houston	0.7761848	51
Lincoln	0.7279522	4
Los Angeles	0.7365210	215
New Orleans	0.7919442	3
New York City	0.7113340	325
Seattle	0.7223629	24
St. Louis	0.8194414	12

Unique Movies

allmovies508<-unique(tweets508[c("movie")]) # get unique movies
allmovies508$num<-seq.int(nrow(allmovies508)) # add counter row
kable(allmovies508) #show unique values for movie name

	movie	num
1	Mothers and Daughters	1
21	Elstree 1976	2
22	Those People	3
24	Being Charlie	4
28	The Offering	5
30	Dark Horse	6
39	Captain America: Civil War	7
545	A Bigger Splash	8
558	Baaghi	9
560	The Family Fang	10
561	The Man Who Knew Infinity	11
563	A Beautiful Planet	12
564	Dough	13
565	Mothers Day	14
620	Papa: Hemingway in Cuba	15
621	Ratchet & Clank	16
639	Viva	17
640	Keanu	18
671	Nina	19
674	Elvis & Nixon	20
676	The Meddler	21
682	Green Room	22
695	Sin Alas	23
696	Mother’s Day	24

Graphs

ggplot(
  moviesum508, aes(x = reorder(movie,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("Movie Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="Movies",y="Score")

ggplot(
  citysum508, aes(x = reorder(city,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("City Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="City",y="Score")

2016-05-09

Import CSV

x509 <- getURL("https://raw.githubusercontent.com/spsstudent15/Data607FinalProject/master/Tweets%20for%2005.09.2016.csv") #import twitter CSV
tweets509<- data.frame(read.csv(text=x509, header=T)) #create data frame
kable(head(tweets509,3)) #show head

X	tweet	city	movie	day	Sentiment_Score
1	Movie Review “A Bigger Splash” starring Tilda Swinton https://t.co/YEbptbaJ4D	New York City	A Bigger Splash	05.09.2016	0.5507142
2	#MovieReview #ABiggerSplash https://t.co/Ko8w27wKSl	New York City	A Bigger Splash	05.09.2016	0.7435926
3	Movie Review #ABiggerSplash https://t.co/Ko8w27wKSl	New York City	A Bigger Splash	05.09.2016	0.8097688

#dim(tweets509)

Movie Score

moviesum509<- ddply(tweets509, .(movie), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by movie
kable(moviesum509)

movie	Sentiment_Score	Count_of_Tweets
A Bigger Splash	0.4746252	11
A Hologram for the King	0.9617668	2
Being Charlie	0.6191784	1
Captain America: Civil War	0.7881106	341
Dark Horse	0.6027937	7
Dough	0.7110656	6
Green Room	0.6466214	7
Keanu	0.7147022	29
Mother’s Day	0.8105354	168
Mothers Day	0.8118599	171
Mothers and Daughters	0.6822596	17
Nina	0.6317530	2
Papa: Hemingway in Cuba	0.0426757	1
Ratchet & Clank	0.6268841	9
The Family Fang	0.6941836	2
The Meddler	0.8436882	9
The Offering	0.0311026	1
Those People	0.6523616	4
Viva	0.6154339	3

Movie and City Score

moviecitysum509<- ddply(tweets509, .(movie, city), summarize,  Sentiment_Score=mean(Sentiment_Score)) #summarize by movie and city
kable(moviecitysum509)

City Score

citysum509<- ddply(tweets509, .(city), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by city
kable(citysum509)

city	Sentiment_Score	Count_of_Tweets
Boston	0.6588172	29
Chicago	0.7317200	67
Denver	0.9195068	21
Houston	0.8627062	48
Los Angeles	0.7929957	268
New Orleans	0.7915382	2
New York City	0.7670166	308
Seattle	0.7480922	34
St. Louis	0.9020215	14

Unique Movies

allmovies509<-unique(tweets509[c("movie")]) # get unique movies
allmovies509$num<-seq.int(nrow(allmovies509)) # add counter row
kable(allmovies509) #show unique values for movie name

	movie	num
1	A Bigger Splash	1
12	A Hologram for the King	2
14	Being Charlie	3
15	Captain America: Civil War	4
356	Dark Horse	5
363	Dough	6
369	Green Room	7
376	Keanu	8
405	Mothers Day	9
576	Mothers and Daughters	10
593	Nina	11
595	Papa: Hemingway in Cuba	12
596	Ratchet & Clank	13
605	The Offering	14
606	The Family Fang	15
608	The Meddler	16
617	Those People	17
621	Viva	18
624	Mother’s Day	19

Graphs

ggplot(
  moviesum509, aes(x = reorder(movie,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("Movie Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="Movies",y="Score")

ggplot(
  citysum509, aes(x = reorder(city,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("City Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="City",y="Score")

All Days Combined

tweets1<- rbind(tweets503,tweets504,tweets505,tweets506,tweets507,tweets508, tweets509)

write.csv(tweets1, file = "tweets503to509.csv")


#kable(head(tweets1))
#kable(tail(tweets1))
#dim(tweets1)

Movie Score

moviesum1<- ddply(tweets1, .(movie), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by movie

moviesum1$movie<-as.character(moviesum1$movie)
moviesum1<- arrange(moviesum1, movie)

moviesum1$num<-seq.int(nrow(moviesum1)) # add counter row

dim(moviesum1)

## [1] 35  4

str(moviesum1)

## 'data.frame':    35 obs. of  4 variables:
##  $ movie          : chr  "A Beautiful Planet" "A Bigger Splash" "A Hologram for the King" "Baaghi" ...
##  $ Sentiment_Score: num  0.715 0.532 0.779 0.594 0.634 ...
##  $ Count_of_Tweets: int  93 51 4 31 17 1508 31 31 14 3 ...
##  $ num            : int  1 2 3 4 5 6 7 8 9 10 ...

kable(moviesum1)

movie	Sentiment_Score	Count_of_Tweets	num
A Beautiful Planet	0.7154244	93	1
A Bigger Splash	0.5321993	51	2
A Hologram for the King	0.7794638	4	3
Baaghi	0.5942856	31	4
Being Charlie	0.6336846	17	5
Captain America: Civil War	0.7840031	1508	6
Dark Horse	0.6607674	31	7
Dough	0.5657804	31	8
Elstree 1976	0.7565491	14	9
Elvis & Nixon	0.6066401	3	10
Eva Hesse	0.8257224	4	11
Green Room	0.6698322	245	12
Hockney	0.5284491	3	13
Keanu	0.6758887	1373	14
LAttesa (The Wait)	0.7607310	3	15
Men & Chicken	0.6999926	12	16
Mother’s Day	0.7698998	283	17
Mothers Day	0.7121606	757	18
Mothers and Daughters	0.6907826	54	19
Nina	0.6563754	14	20
Older Than Ireland	0.3699457	5	21
Pali Road	0.4949967	2	22
Papa: Hemingway in Cuba	0.5584682	40	23
Ratchet & Clank	0.6233490	577	24
Sacrifice	0.7088486	25	25
Sin Alas	0.2750178	2	26
The American Side	0.7633015	2	27
The Family Fang	0.7278845	52	28
The Man Who Knew Infinity	0.8592558	41	29
The Meddler	0.6350935	89	30
The Offering	0.4061673	7	31
Those People	0.4498706	8	32
Transfixed	0.8723244	1	33
Viktoria	0.4935801	5	34
Viva	0.6624109	58	35

Movie and City Score

moviecitysum1<- ddply(tweets1, .(movie, city), summarize,  Sentiment_Score=mean(Sentiment_Score)) #summarize by movie and city

kable(moviecitysum1)

City Score

citysum1<- ddply(tweets1, .(city), summarize,  Sentiment_Score=mean(Sentiment_Score), Count_of_Tweets=length(tweet)) #summarize by city
kable(citysum1)

city	Sentiment_Score	Count_of_Tweets
Boston	0.6685495	207
Chicago	0.6869049	526
Denver	0.7415370	165
Houston	0.7692286	284
Lincoln	0.7168697	12
los Angeles	0.6403698	797
New Orleans	0.6528819	99
New York City	0.7133538	2076
Seattle	0.7025967	218
St. Louis	0.8095269	134
Los Angeles	0.7396053	927

Graphs

ggplot(
  moviesum1, aes(x = reorder(movie,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("Movie Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="Movies",y="Score")

ggplot(
  citysum1, aes(x = reorder(city,Sentiment_Score), y = Sentiment_Score, fill=Sentiment_Score)) + 
  geom_bar(stat="identity") +
  ggtitle("City Average Sentiment Score")+ 
  theme(axis.text=element_text(angle=90))+
  labs(x="City",y="Score")

Statistics

Totals

dim(tweets1)

## [1] 5445    6

dim(allmovies1)

## [1] 35  2

Tweet Count Per Day

dim(tweets503)

## [1] 2440    6

dim(tweets504)

## [1] 184   6

dim(tweets505)

## [1] 124   6

dim(tweets506)

## [1] 125   6

dim(tweets507)

## [1] 1031    6

dim(tweets508)

## [1] 750   6

dim(tweets509)

## [1] 791   6

Movie Count Per Day

dim(allmovies503)

## [1] 22  2

dim(allmovies504)

## [1] 14  2

dim(allmovies505)

## [1] 13  2

dim(allmovies506)

## [1] 14  2

dim(allmovies507)

## [1] 25  2

dim(allmovies508)

## [1] 24  2

dim(allmovies509)

## [1] 19  2

Twitter Summary

Armenoush Aslanian-Persico

Libraries

Sources

2016-05-03

Import CSV

Movie Score

Movie and City Score

City Score

Unique Movies

Graphs

2016-05-04

Import CSV

Movie Score

Movie and City Score

City Score

Unique Movies

Graphs

2016-05-05

Import CSV

Movie Score

Movie and City Score

City Score

Unique Movies

Graphs

2016-05-06

Import CSV

Movie Score

Movie and City Score

City Score

Unique Movies

Graphs

2016-05-07

Import CSV

Movie Score

Movie and City Score

City Score

Unique Movies

Graphs

2016-05-08

Import CSV

Movie Score

Movie and City Score

City Score

Unique Movies

Graphs

2016-05-09

Import CSV

Movie Score

Movie and City Score

City Score

Unique Movies

Graphs

All Days Combined

Movie Score

Movie and City Score

City Score

Graphs

Statistics

Totals

Tweet Count Per Day

Movie Count Per Day