NOTA IMDB E LUCRO
library(tidyverse)
imdb <- read_rds("../dados/imdb.rds")
imdb %>%
mutate(lucro = receita-orcamento) %>%
summarise(m_duracao = mean(duracao, na.rm = TRUE),
m_orcamento = mean(orcamento, na.rm=TRUE),
m_nota_meia = mean(nota_imdb, na.rm=TRUE),
m_lucro = mean(lucro, na.rm=TRUE),
num_films = n()) %>%
knitr::kable(caption = "Meia das variables do estudio", digits=2, format.args = list(big.mark = ",",
scientific = FALSE))
Meia das variables do estudio
| 106.37 |
35,237,114 |
6.37 |
17,161,639 |
3,713 |
imdb %>%
group_by(nota_imdb) %>%
mutate(lucro = receita-orcamento) %>%
mutate(lucrou = ifelse(lucro>0, "SI","NO"))%>%
ggplot() +
geom_point(aes(x = lucro, y = nota_imdb, color = lucrou))+
geom_abline(intercept = 0, slope = 1, color = "blue")+
labs(
title = "Gráfico de dispersão",
subtitle = "Lucro vs Nota Imdb" )
imdb %>%
#group_by() %>%
mutate(lucro = receita-orcamento) %>%
mutate(lucrou = ifelse(lucro>0, "SI","NO"))%>%
ggplot() +
geom_point(aes(x = orcamento, y = lucro, color = lucrou))+
geom_hline(yintercept = 0,color = "blue")+
labs(
title = "Gráfico de dispersão",
subtitle = "Lucro vs Orcamento" )
nota1<-imdb %>%
mutate(lucro = receita-orcamento) %>%
group_by(nota_imdb) %>%
summarise(lucro_medio = mean(lucro, na.rm = TRUE),
duracao_meia= mean(duracao, na.rm=TRUE),
orcamento_medio=mean(orcamento,na.rm = TRUE),
num_films = n()) %>%
arrange(desc(nota_imdb)) %>%
top_n (50,nota_imdb)
nota1 %>%
knitr::kable(caption = "LUCRO MEDIO POR NOTA IMDB", format.args = list(big.mark = ",",
scientific = FALSE))
LUCRO MEDIO POR NOTA IMDB
| 9.3 |
3,341,469.0 |
142.00000 |
25,000,000 |
1 |
| 9.2 |
128,821,952.0 |
175.00000 |
6,000,000 |
1 |
| 9.1 |
NaN |
90.00000 |
17,000,000 |
1 |
| 9.0 |
196,308,030.5 |
141.66667 |
99,000,000 |
3 |
| 8.9 |
152,338,810.3 |
162.75000 |
31,087,500 |
4 |
| 8.8 |
163,360,548.2 |
107.33333 |
74,000,000 |
6 |
| 8.7 |
186,846,842.0 |
105.66667 |
32,930,000 |
9 |
| 8.6 |
51,873,008.9 |
107.00000 |
31,113,000 |
12 |
| 8.5 |
98,526,189.5 |
129.61111 |
54,837,934 |
18 |
| 8.4 |
63,268,178.8 |
98.00000 |
26,942,308 |
17 |
| 8.3 |
77,955,748.7 |
122.82759 |
40,745,586 |
29 |
| 8.2 |
62,310,335.4 |
120.72000 |
41,293,478 |
25 |
| 8.1 |
89,883,063.2 |
119.56818 |
41,408,810 |
45 |
| 8.0 |
63,271,062.1 |
132.52000 |
30,189,362 |
50 |
| 7.9 |
64,981,687.6 |
123.02083 |
53,313,750 |
48 |
| 7.8 |
37,923,287.5 |
111.17391 |
37,757,620 |
69 |
| 7.7 |
44,638,976.9 |
115.83871 |
34,068,791 |
62 |
| 7.6 |
42,396,896.3 |
120.75281 |
34,392,993 |
89 |
| 7.5 |
30,993,385.4 |
106.32941 |
32,549,731 |
85 |
| 7.4 |
21,254,637.4 |
109.75532 |
25,931,335 |
94 |
| 7.3 |
34,075,561.5 |
108.69672 |
41,713,137 |
122 |
| 7.2 |
29,162,619.9 |
112.88636 |
35,397,813 |
133 |
| 7.1 |
14,654,894.1 |
106.78400 |
32,812,070 |
125 |
| 7.0 |
22,197,595.9 |
108.00000 |
37,206,352 |
128 |
| 6.9 |
23,340,037.0 |
111.61789 |
37,997,908 |
123 |
| 6.8 |
12,222,904.8 |
108.40000 |
31,548,102 |
135 |
| 6.7 |
13,048,874.7 |
109.16168 |
40,519,064 |
168 |
| 6.6 |
11,116,086.2 |
108.28846 |
40,070,354 |
156 |
| 6.5 |
14,288,025.4 |
106.73288 |
35,481,415 |
146 |
| 6.4 |
14,869,558.9 |
108.12414 |
42,117,949 |
145 |
| 6.3 |
4,950,227.4 |
104.95420 |
40,280,251 |
131 |
| 6.2 |
6,681,730.8 |
102.85496 |
33,368,742 |
131 |
| 6.1 |
10,601,720.2 |
104.93130 |
42,186,967 |
131 |
| 6.0 |
6,950,785.8 |
106.60000 |
39,477,326 |
95 |
| 5.9 |
3,721,166.4 |
101.77778 |
32,637,712 |
126 |
| 5.8 |
-446,488.8 |
102.68367 |
44,016,882 |
98 |
| 5.7 |
9,979,507.5 |
102.30000 |
30,475,116 |
90 |
| 5.6 |
-4,660,166.0 |
101.32584 |
37,441,131 |
89 |
| 5.5 |
5,223,751.5 |
100.37500 |
39,609,392 |
80 |
| 5.4 |
-3,564,249.4 |
98.90909 |
35,748,831 |
88 |
| 5.3 |
-6,985,906.2 |
97.95775 |
24,000,145 |
71 |
| 5.2 |
9,280,941.3 |
95.77193 |
30,035,717 |
57 |
| 5.1 |
713,842.1 |
97.05357 |
26,706,019 |
57 |
| 5.0 |
5,379,061.4 |
101.64706 |
24,623,387 |
34 |
| 4.9 |
437,100.5 |
97.45238 |
36,057,436 |
42 |
| 4.8 |
-1,719,612.2 |
95.52632 |
28,914,278 |
38 |
| 4.7 |
-6,866,391.7 |
94.09091 |
24,455,263 |
23 |
| 4.6 |
19,591,424.0 |
95.20588 |
20,768,750 |
34 |
| 4.5 |
5,915,980.4 |
96.03704 |
19,622,609 |
27 |
| 4.4 |
6,886,197.9 |
96.00000 |
25,737,500 |
20 |
ESTUDIANDO POR GENERO DE FILMS
imdb %>%
group_by(generos) %>%
mutate(lucro = receita-orcamento) %>%
summarise(nota_media = mean (nota_imdb, na.rm = TRUE),
media_orcamento = mean (orcamento, na.rm = TRUE),
media_lucro = mean (lucro, na.rm = TRUE),
num_films = n()) %>%
arrange(desc(num_films) ) %>%
top_n(20,num_films) %>%
knitr::kable(caption = "GENEROS CON MAIOR NUMERO DE FILMS", format.args = list(big.mark = ",",
scientific = FALSE))
GENEROS CON MAIOR NUMERO DE FILMS
| Comedy |
5.776216 |
20,211,987 |
21,367,568 |
185 |
| Drama |
6.933133 |
12,033,697 |
8,524,681 |
166 |
| Comedy|Drama |
6.496710 |
14,495,104 |
11,310,121 |
152 |
| Comedy|Drama|Romance |
6.429530 |
21,147,200 |
11,531,093 |
149 |
| Comedy|Romance |
5.894815 |
25,040,242 |
22,992,323 |
135 |
| Drama|Romance |
6.841748 |
20,609,415 |
12,055,360 |
103 |
| Crime|Drama|Thriller |
6.675343 |
25,664,160 |
10,103,622 |
73 |
| Horror |
5.392727 |
8,462,019 |
33,117,199 |
55 |
| Action|Adventure|Sci-Fi |
6.633333 |
144,115,556 |
43,027,809 |
45 |
| Action|Crime|Thriller |
6.288889 |
45,044,444 |
12,316,009 |
45 |
| Action|Crime|Drama|Thriller |
6.370455 |
36,995,122 |
4,035,793 |
44 |
| Crime|Drama |
7.306818 |
14,462,250 |
16,159,900 |
44 |
| Comedy|Crime |
5.869767 |
25,785,366 |
19,280,536 |
43 |
| Horror|Thriller |
5.361905 |
9,281,501 |
16,405,033 |
42 |
| Drama|Thriller |
6.267500 |
22,160,417 |
8,788,240 |
40 |
| Crime|Drama|Mystery|Thriller |
6.966667 |
32,992,000 |
14,269,760 |
39 |
| Documentary |
6.991667 |
1,067,132 |
1,247,920 |
36 |
| Horror|Mystery|Thriller |
5.893548 |
17,015,757 |
23,602,440 |
31 |
| Action|Adventure|Sci-Fi|Thriller |
6.300000 |
103,107,692 |
18,122,529 |
26 |
| Adventure|Animation|Comedy|Family|Fantasy |
6.430769 |
96,000,000 |
54,891,179 |
26 |
| Drama|Sport |
7.123077 |
18,772,174 |
19,222,457 |
26 |
imdb %>%
group_by(generos) %>%
mutate(lucro = receita-orcamento) %>%
summarise(nota_media = mean (nota_imdb, na.rm = TRUE),
media_orcamento = mean (orcamento, na.rm = TRUE),
media_lucro = mean (lucro, na.rm = TRUE),
num_films = n()) %>%
arrange(desc(media_lucro) ) %>%
top_n(20,media_lucro) %>%
knitr::kable(caption = "GENEROS CON LUCRO MAIS ELEVADO", digits=2, format.args = list(big.mark = ",",
scientific = FALSE))
GENEROS CON LUCRO MAIS ELEVADO
| Family|Sci-Fi |
5.65 |
5,425,000 |
424,449,459 |
2 |
| Adventure|Animation|Drama|Family|Musical |
8.50 |
45,000,000 |
377,783,777 |
1 |
| Action|Biography|Drama|History|Thriller|War |
7.30 |
58,800,000 |
291,323,553 |
1 |
| Adventure|Drama|Fantasy|Romance |
5.00 |
79,333,333 |
217,148,557 |
3 |
| Action|Adventure|Fantasy|Sci-Fi |
6.98 |
97,125,000 |
199,559,758 |
13 |
| Drama|Fantasy|Romance|Thriller |
7.00 |
22,000,000 |
195,631,306 |
1 |
| Drama|History|Romance|War |
7.20 |
4,488,500 |
194,678,278 |
2 |
| Adventure|Animation|Comedy|Drama|Family|Fantasy |
8.30 |
175,000,000 |
181,454,367 |
1 |
| Action|Adventure|Animation|Family |
8.00 |
92,000,000 |
169,437,578 |
1 |
| Adventure|Comedy|Family|Mystery|Sci-Fi |
7.30 |
90,000,000 |
160,147,615 |
1 |
| Animation|Comedy|Family|Sci-Fi |
7.25 |
88,000,000 |
158,459,955 |
2 |
| Adventure|Drama|Sci-Fi|Thriller |
7.45 |
73,750,000 |
157,360,628 |
2 |
| Biography|Drama|Family|Musical|Romance |
8.00 |
8,200,000 |
155,014,286 |
1 |
| Animation|Comedy|Family|Fantasy|Music |
4.85 |
67,500,000 |
150,969,864 |
2 |
| Adventure|Sci-Fi|Thriller |
6.80 |
108,333,333 |
148,946,823 |
6 |
| Adventure|Animation|Comedy|Family|Fantasy|Romance |
7.25 |
100,000,000 |
143,310,828 |
2 |
| Action|Adventure|Comedy|Romance|Sci-Fi |
6.13 |
34,000,000 |
143,160,018 |
3 |
| Action|Adventure|Comedy|Family|Fantasy |
6.40 |
110,000,000 |
140,863,268 |
1 |
| Action|Animation|Comedy|Family|Sci-Fi |
6.85 |
102,000,000 |
140,183,548 |
2 |
| Action|Adventure|Crime|Drama|Mystery|Thriller |
7.80 |
44,000,000 |
139,875,760 |
1 |
ESTUDIANDO POR DIRECTORES
imdb %>%
mutate(lucro = receita-orcamento) %>%
group_by(diretor) %>%
summarise(lucro_medio = mean(lucro, na.rm = TRUE),
nota_media = mean(nota_imdb, na.rm = TRUE),
num_films = n()) %>%
#top_n (20,lucro_medio) %>%
arrange(desc(lucro_medio)) %>%
top_n (20,lucro_medio) %>%
knitr::kable(caption = "20 DIRECTORES CON LUCRO MEDIO MAIS ELEVADO", digits=2, format.args = list(big.mark = ",",
scientific = FALSE))
20 DIRECTORES CON LUCRO MEDIO MAIS ELEVADO
| Tim Miller |
305,024,263 |
8.10 |
1 |
| George Lucas |
277,328,296 |
7.40 |
5 |
| Richard Marquand |
276,625,409 |
8.40 |
1 |
| Irvin Kershner |
272,158,751 |
8.80 |
1 |
| Kyle Balda |
262,029,560 |
6.40 |
1 |
| Colin Trevorrow |
252,717,532 |
7.00 |
2 |
| Chris Buck |
250,736,600 |
7.60 |
1 |
| Pierre Coffin |
237,275,640 |
7.60 |
2 |
| Lee Unkrich |
214,984,497 |
8.30 |
1 |
| Joss Whedon |
199,202,360 |
7.87 |
3 |
| James Cameron |
194,620,985 |
7.88 |
6 |
| Roger Allers |
188,543,668 |
7.35 |
2 |
| William Cottrell |
182,925,485 |
7.70 |
1 |
| Pete Docter |
158,113,780 |
8.23 |
3 |
| Francis Lawrence |
151,100,394 |
7.00 |
5 |
| Daniel Myrick |
140,470,114 |
6.40 |
1 |
| Peter Jackson |
132,967,515 |
8.02 |
5 |
| Andrew Adamson |
130,611,730 |
7.08 |
5 |
| Joel Zwick |
129,275,992 |
5.45 |
2 |
| Sam Taylor-Johnson |
126,147,885 |
4.10 |
1 |
imdb %>%
mutate(lucro = receita-orcamento) %>%
group_by(diretor) %>%
summarise(lucro_medio = mean(lucro, na.rm = TRUE),
nota_media = mean(nota_imdb, na.rm = TRUE),
num_films = n()) %>%
#top_n (20,lucro_medio) %>%
arrange(desc(nota_media)) %>%
top_n (20,nota_media) %>%
knitr::kable(caption = "20 DIRECTORES CON NOTA MEIA MAIS ELEVADA", digits=2, format.args = list(big.mark = ",",
scientific = FALSE))
20 DIRECTORES CON NOTA MEIA MAIS ELEVADA
| Irvin Kershner |
272,158,751 |
8.80 |
1 |
| Cary Bell |
NaN |
8.70 |
1 |
| Mitchell Altieri |
NaN |
8.70 |
1 |
| Charles Chaplin |
-1,336,755 |
8.60 |
1 |
| Mike Mayhall |
NaN |
8.60 |
1 |
| Damien Chazelle |
9,792,000 |
8.50 |
1 |
| Milos Forman |
70,600,000 |
8.50 |
2 |
| Ron Fricke |
-1,398,153 |
8.50 |
1 |
| Stanley Kubrick |
NaN |
8.45 |
2 |
| Christopher Nolan |
101,028,447 |
8.43 |
8 |
| Bill Melendez |
NaN |
8.40 |
1 |
| Catherine Owens |
NaN |
8.40 |
1 |
| Jay Oliva |
NaN |
8.40 |
1 |
| Marius A. Markevicius |
-366,222 |
8.40 |
1 |
| Richard Marquand |
276,625,409 |
8.40 |
1 |
| Robert Mulligan |
NaN |
8.40 |
1 |
| John Sturges |
NaN |
8.30 |
1 |
| Justin Paul Miller |
NaN |
8.30 |
1 |
| Lee Unkrich |
214,984,497 |
8.30 |
1 |
| Stanley Donen |
NaN |
8.30 |
1 |
| Sut Jhally |
NaN |
8.30 |
1 |
RELACION ENTRE DURACION E LUCRO
graf<-imdb %>%
mutate(lucro = receita-orcamento) %>%
mutate(lucrou = ifelse(lucro>0, "SI","NO"))%>%
group_by(duracao) %>%
summarise(nota_media = mean(nota_imdb, na.rm = TRUE),
lucro_medio = mean(lucro, na.rm=TRUE),
num_films = n()) %>%
arrange(desc(lucro_medio)) %>%
top_n (20,lucro_medio)
graf %>%
knitr::kable(caption = "MAIOR LUCRO POR DURACAO", digits=2, format.args = list(big.mark = ",",
scientific = FALSE))
MAIOR LUCRO POR DURACAO
| 173 |
6.55 |
403,279,547 |
2 |
| 192 |
8.90 |
283,019,252 |
1 |
| 195 |
7.35 |
208,992,272 |
2 |
| 226 |
8.20 |
194,678,278 |
1 |
| 194 |
7.45 |
188,034,500 |
2 |
| 73 |
7.15 |
186,209,118 |
2 |
| 236 |
8.00 |
162,208,848 |
1 |
| 167 |
7.90 |
133,029,270 |
1 |
| 174 |
7.30 |
123,775,212 |
2 |
| 182 |
7.90 |
123,001,229 |
1 |
| 178 |
8.00 |
101,231,080 |
7 |
| 200 |
8.00 |
100,722,000 |
1 |
| 164 |
8.05 |
99,752,114 |
2 |
| 151 |
8.20 |
83,715,114 |
5 |
| 154 |
7.24 |
83,262,234 |
10 |
| 183 |
6.90 |
80,249,062 |
1 |
| 142 |
7.30 |
80,205,771 |
12 |
| 172 |
7.62 |
78,623,982 |
6 |
| 175 |
8.30 |
76,810,976 |
2 |
| 190 |
7.60 |
76,107,476 |
1 |
imdb %>%
mutate(lucro = receita-orcamento) %>%
mutate(lucrou = ifelse(lucro>0, "SI","NO"))%>%
ggplot() +
geom_point(aes(x = lucro, y = duracao, color = lucrou))+
geom_abline(intercept = 0, slope = 1, color = "blue")+
labs(
title = "Gráfico de dispersão",
subtitle = "Lucro vs Duracao" )
CONCLUSION
Athos e o Fernando deverian investir no filme con arreglo as siguientes variables
Num_films<-nota1$num_films
vMax=max(Num_films)
nota1 %>% filter(num_films==vMax) %>%
select(-"num_films")%>%
knitr::kable(caption = " ",
digits=2,format.args = list(big.mark = ",",
scientific = FALSE),col.names=c("Nota","Lucro","Duracao","Orcamento"))
| 6.7 |
13,048,875 |
109.16 |
40,519,064 |