library(reticulate)
# create a new environment
# conda_create("r-reticulate")
# install Matplotlib
# conda_install("r-reticulate", "matplotlib")
# import Matplotlib (it will be automatically discovered in "r-reticulate")
plt <- import("matplotlib")
np <- import("numpy")

# From Double get integers 
# TC y
TC_all$TC_sum_all <- as.integer(TC_all$TC_sum_all)

import matplotlib.pyplot as plt
import numpy as np
from matplotlib.ticker import FuncFormatter
# ax=axes
fig, ax = plt.subplots()
# First plot Total Publications - time series
ax.plot(tpx, tpy, color='r',marker='o', label='Total Publications')
ax.set_xlabel('Year')
ax.set_ylabel('Total Publications', color='r')
# Customization for bar charts
barw = 0.5
ax.bar(sx, sy, color='g', label = 'Scopus', alpha = 0.5, width=barw)

ax.bar(wx1, wy, color='orange', label = 'WoS', alpha=0.8, width=barw)
# Y2 - Total citations

twin_axes = ax.twinx()
twin_axes.plot(tcx, tcy, color = 'purple',marker='o', label='Total Citations')
twin_axes.set_ylabel('Total Citations', color='purple')
# Customize
plt.title('Total Scientific Production vs. Total Citations')
# y2 Total Citation label location
plt.legend(loc='center left')
# True or False to get the grid at the background
ax.grid(False)
# y1 label location
ax.legend(loc='upper left')
# Y2 limit depends of tcy scale in this case 1400 improves label location
plt.ylim(0, 1300) #########  <-----Important--------- """"Change Y2 Coordinate"""""
# plt.annotate() customize numbers for each position

for i, label in enumerate(tcy):
  plt.annotate(label, (tcx[i], tcy[i] + 0.5), color='purple', size=8)

for i, label in enumerate(tpy):
  ax.annotate(label, (tpx[i], tpy[i] + 0.8), color='red', size=8)

for i, label in enumerate(wy):
  ax.annotate(label, (wx1[i], wy[i] + 0.1), color='brown', size=8)

for i, label in enumerate(sy):
  ax.annotate(label, (sx[i], sy[i] + 0.2),color='green', size=8)

# Rotate x ticks
plt.xticks(tpx)

fig.autofmt_xdate(rotation = 70)
# The Y1 ticks depends from tpy scale limits
yticks = [0, 10,20,30,40,50] ########## <-----Important---- Choose scale .. just specify which numbers you want
ax.set_yticks(yticks)
# Export Figure as SVG
plt.savefig("ScientificProd_john_edison_ai_math.svg")

plt.show()

table_2_country |>
  DT::datatable(class = "cell-border stripe", 
                rownames = F, 
                filter = "top", 
                editable = FALSE, 
                extensions = "Buttons", 
                options = list(dom = "Bfrtip",
                               buttons = c("copy",
                                           "csv",
                                           "excel", 
                                           "pdf", 
                                           "print")))

figure_2a <- 
  figure_2_country_wos_scopus_1 |>
  activate(edges) |> 
  # tidygraph::rename(weight = n) |> 
  ggraph(layout = "graphopt") +
  geom_edge_link(aes(width = Weight),
                 colour = "lightgray") +
  scale_edge_width(name = "Link strength") +
  geom_node_point(aes(color = community, 
                      size = degree)) +
  geom_node_text(aes(label = name), repel = TRUE) +
  scale_size(name = "Degree") +
  # scale_color_binned(name = "Communities") +
  theme_graph()

figure_2a

figure_2b <- 
  figure_2_country_wos_scopus_1 |> 
  activate(nodes) |> 
  data.frame() |> 
  group_by(community) |> 
  dplyr::count(community, sort = TRUE) |> 
  slice(1:10) |>  
  ggplot(aes(x = reorder(community, n), y = n)) +
  geom_point(stat = "identity") +
  geom_line(group = 1) + 
  # geom_text(label = as.numeric(community),
  #           nudge_x = 0.5,
  #           nudge_y = 0.5,
  #           check_overlap = T) +
  labs(title = "Communities by size", 
       x = "communities", 
       y = "Countries") +
  theme(text = element_text(color = "black",
                            face = "bold",
                            family = "Times New Roman"),
        plot.title = element_text(size = 25),
        panel.background = element_rect(fill = "white"), 
        axis.text.y = element_text(size = 15, 
                                   colour = "black"),
        axis.text.x = element_text(size = 15,
                                   colour = "black"),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20)
        ) 

figure_2b

# Create a dataframe with links 
figure_2c_edges <- 
  figure_2_country_wos_scopus |>
  dplyr::filter(from != to) |> 
  tidygraph::as_tbl_graph() |> 
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(year = PY) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= 2002,
                year <= 2022) |> 
  dplyr::mutate(percentage = n/max(n)) |> 
  dplyr::select(year, percentage)
# Create a data frame with author and year 
figure_2c_nodes <- # 21 row 
  figure_2_country_wos_scopus |>
  dplyr::filter(from != to) |> 
  tidygraph::as_tbl_graph() |> 
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(CO = from, 
                year = PY) |>
  bind_rows(figure_2_country_wos_scopus |>  
              tidygraph::as_tbl_graph() |> 
              tidygraph::activate(edges) |> 
              tidygraph::as_tibble() |> 
              dplyr::select(CO = to, 
                            year = PY)) |> 
  unique() |> 
  dplyr::group_by(CO) |> 
  dplyr::slice(which.min(year)) |>
  dplyr::ungroup() |> 
  dplyr::select(year) |> 
  dplyr::group_by(year) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= 2002,
                year <= 2022) |> 
  dplyr::ungroup() |> 
  dplyr::mutate(percentage = n / max(n)) |> 
  select(year, percentage)

figure_2c <- 
  figure_2c_nodes |> 
  mutate(type = "nodes",
         year = as.numeric(year)) |> 
  bind_rows(figure_2c_edges |> 
              mutate(type = "links",
                     year = as.numeric(year))) |> 
  ggplot(aes(x = year, 
             y = percentage, 
             color = type)) +
  geom_point() +
  geom_line() +
  theme(legend.position = "right", 
        text = element_text(color = "black", 
                            face = "bold",
                            family = "Times"),
        plot.title = element_text(size = 25),
        panel.background = element_rect(fill = "white"), 
        axis.text.y = element_text(size = 15, 
                                   colour = "black"),
        axis.text.x = element_text(size = 15,
                                   colour = "black", 
                                   angle = 45, vjust = 0.5
        ),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20),
        legend.text = element_text(size = "15"),
        legend.title = element_blank()) +
  labs(title = "Nodes and links through time", 
       y = "Percentage") +
  scale_y_continuous(labels = scales::percent) +
  scale_x_continuous(breaks = seq(2002, 2022, by = 1))

figure_2c

table_3_journal |> 
  arrange(desc(total)) |> 
  DT::datatable(class = "cell-border stripe", 
                rownames = F, 
                filter = "top", 
                editable = FALSE, 
                extensions = "Buttons", 
                options = list(dom = "Bfrtip",
                               buttons = c("copy",
                                           "csv",
                                           "excel", 
                                           "pdf", 
                                           "print")))

journal_citation_graph_weighted_tbl_small <-
  journal_df |>
  dplyr::select(JI_main, JI_ref) |>
  dplyr::group_by(JI_main, JI_ref) |>
  dplyr::count() |>
  dplyr::rename(weight = n) |>
  as_tbl_graph(directed = FALSE) |>
  # convert(to_simple) |>
  activate(nodes) |>
  dplyr::mutate(components = tidygraph::group_components(type = "weak"))  |>
  dplyr::filter(components == 1) |>
  activate(nodes) |>
  dplyr::mutate(degree = centrality_degree(),
                community = tidygraph::group_louvain()) |>
  dplyr::select(-components) |>
  dplyr::filter(degree >= 1)

figure_3a_1 <- 
  SO_edges %>% 
  tidygraph::as_tbl_graph() %>% 
  tidygraph::activate(nodes) %>% 
  # tidygraph::mutate(id = name) %>% 
  tidygraph::left_join(SO_nodes, by = c("name" = "id")) %>% 
  tidygraph::select(-name) %>% 
  tidygraph::rename(name = Label) %>% 
  ggraph(layout = "graphopt") +
  geom_edge_link(aes(width = weight),
                 colour = "lightgray") +
  scale_edge_width(name = "Link strength") +
  geom_node_point(aes(color = community, 
                      size = degree)) +
  geom_node_text(aes(label = name), repel = TRUE) +
  scale_size(name = "Degree") +
  # scale_color_binned(name = "Communities") +
  theme_graph()

figure_3a_1

figure_3b <- 
  journal_citation_graph_weighted_tbl_small |> 
  activate(nodes) |> 
  data.frame() |> 
  dplyr::select(community) |> 
  dplyr::count(community, sort = TRUE) |> 
  dplyr::slice(1:10) |> 
  ggplot(aes(x = reorder(community, n), y = n)) +
  geom_point(stat = "identity") +
  geom_line(group = 1) + 
  # geom_text(label = as.numeric(community),
  #           nudge_x = 0.5,
  #           nudge_y = 0.5,
  #           check_overlap = T) +
  labs(title = "Communities by size", 
       x = "communities", 
       y = "Journals") +
  theme(text = element_text(color = "black",
                            face = "bold",
                            family = "Times"),
        plot.title = element_text(size = 25),
        panel.background = element_rect(fill = "white"), 
        axis.text.y = element_text(size = 15, 
                                   colour = "black"),
        axis.text.x = element_text(size = 15,
                                   colour = "black"),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20)
        ) 
figure_3b

# Create a dataframe with links 
figure_3c_edges <- 
  journal_df |>
  select(from = JI_main, to = JI_ref, PY = PY_ref) %>% 
  dplyr::filter(from != to) |> 
  tidygraph::as_tbl_graph() |> 
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(year = PY) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= 2002,
                year <= 2022) |> 
  dplyr::mutate(percentage = n/max(n)) |> 
  dplyr::select(year, percentage)
# Create a data frame with author and year 
figure_3c_nodes <- # 21 row 
  journal_df |>
  select(from = JI_main, to = JI_ref, PY = PY_ref) %>% 
  dplyr::filter(from != to) |> 
  tidygraph::as_tbl_graph() |> 
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(CO = from, 
                year = PY) |>
  bind_rows(journal_df |>
              select(from = JI_main, 
                     to = JI_ref, 
                     PY = PY_ref) %>%  
              tidygraph::as_tbl_graph() |> 
              tidygraph::activate(edges) |> 
              tidygraph::as_tibble() |> 
              dplyr::select(CO = to, 
                            year = PY)) |> 
  unique() |> 
  dplyr::group_by(CO) |> 
  dplyr::slice(which.min(year)) |>
  dplyr::ungroup() |> 
  dplyr::select(year) |> 
  dplyr::group_by(year) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= 2002,
                year <= 2022) |> 
  dplyr::ungroup() |> 
  dplyr::mutate(percentage = n / max(n)) |> 
  select(year, percentage)

figure_3c <- 
  figure_3c_nodes |> 
  mutate(type = "nodes") |> 
  bind_rows(figure_3c_edges |> 
              mutate(type = "links")) |> 
  ggplot(aes(x = year, 
             y = percentage, 
             color = type)) +
  geom_point() +
  geom_line() +
  theme(legend.position = "right", 
        text = element_text(color = "black", 
                            face = "bold",
                            family = "Times"),
        plot.title = element_text(size = 25),
        panel.background = element_rect(fill = "white"), 
        axis.text.y = element_text(size = 15, 
                                   colour = "black"),
        axis.text.x = element_text(size = 15,
                                   colour = "black", 
                                   angle = 45, vjust = 0.5
        ),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20),
        legend.text = element_text(size = "15"),
        legend.title = element_blank()) +
  labs(title = "Nodes and links through time", 
       y = "Percentage") +
  scale_y_continuous(labels = scales::percent) +
  scale_x_continuous(breaks = seq(2002, 2022, by = 1))

figure_3c

table_4_authors |> 
  dplyr::select(authors_total, papers_total) %>% 
  DT::datatable(class = "cell-border stripe", 
                rownames = F, 
                filter = "top", 
                editable = FALSE, 
                extensions = "Buttons", 
                options = list(dom = "Bfrtip",
                               buttons = c("copy",
                                           "csv",
                                           "excel", 
                                           "pdf", 
                                           "print")))

author_network_time <- 
  author_df |> 
  tidygraph::as_tbl_graph(directed = FALSE) |> 
  activate(nodes) |> 
  dplyr::mutate(components = tidygraph::group_components(type = "weak")) |> 
  dplyr::filter(components == 1) |> 
  dplyr::mutate(degree = centrality_degree(),
                community = as.factor(group_louvain()))

author_network <- 
  author_df |> 
  dplyr::select(-PY) |> 
  dplyr::group_by(from, to) |> 
  dplyr::count() |> 
  dplyr::rename(weight = n) |> 
  tidygraph::as_tbl_graph(directed = FALSE) |> 
  activate(nodes) |> 
  # dplyr::mutate(components = tidygraph::group_components(type = "weak")) |> 
  # dplyr::filter(components == 1) |> 
  dplyr::mutate(degree = centrality_degree(),
                community = as.factor(group_louvain()))

figure_4a <- 
  author_network |> 
  activate(nodes) |> 
  data.frame() |> 
  dplyr::count(community) |>
  slice(1:10) |>  
  ggplot(aes(x = reorder(community, n), y = n)) +
  geom_point(stat = "identity") +
  geom_line(group = 1) + 
  # geom_text(label = as.numeric(community),
  #           nudge_x = 0.5,
  #           nudge_y = 0.5,
  #           check_overlap = T) +
  labs(title = "Communities by size", 
       x = "communities", 
       y = "Authors") +
  theme(text = element_text(color = "black",
                            face = "bold",
                            family = "Times"),
        plot.title = element_text(size = 25),
        panel.background = element_rect(fill = "white"), 
        axis.text.y = element_text(size = 15, 
                                   colour = "black"),
        axis.text.x = element_text(size = 15,
                                   colour = "black"),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20)
        ) 

figure_4a

# Create a dataframe with links 
fig_1c_edges <- 
  author_network_time |>
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(year = PY) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= 2002,
                year <= 2022) |> 
  dplyr::mutate(percentage = n/max(n)) |> 
  dplyr::select(year, percentage)
# Create a data frame with author and year 
fig_1c_nodes <- # 21 row 
  author_network_time |>
  activate(edges) |> 
  as_tibble() |> 
  dplyr::select(author = from, 
                year = PY) |>
  bind_rows(author_network_time |> 
              activate(edges) |> 
              as_tibble() |> 
              dplyr::select(author = to, 
                            year = PY)) |> 
  unique() |> 
  dplyr::group_by(author) |> 
  dplyr::slice(which.min(year)) |>
  dplyr::ungroup() |> 
  dplyr::select(year) |> 
  dplyr::group_by(year) |> 
  dplyr::count(year) |> 
  dplyr::filter(year >= 2002,
                year <= 2022) |> 
  dplyr::ungroup() |> 
  dplyr::mutate(percentage = n / max(n)) |> 
  select(year, percentage)

figure_4b <- 
  fig_1c_nodes |> 
  mutate(type = "nodes") |> 
  bind_rows(fig_1c_edges |> 
              mutate(type = "links")) |> 
  ggplot(aes(x = year, 
             y = percentage, 
             color = type)) +
  geom_point() +
  geom_line() +
  theme(legend.position = "right", 
        text = element_text(color = "black", 
                            face = "bold",
                            family = "Times"),
        plot.title = element_text(size = 25),
        panel.background = element_rect(fill = "white"), 
        axis.text.y = element_text(size = 15, 
                                   colour = "black"),
        axis.text.x = element_text(size = 15,
                                   colour = "black", 
                                   angle = 45, vjust = 0.5
        ),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20),
        legend.text = element_text(size = "15"),
        legend.title = element_blank()) +
  labs(title = "Nodes and links through time", 
       y = "Percentage") +
  scale_y_continuous(labels = scales::percent) +
  scale_x_continuous(breaks = seq(2002, 2022, by = 1))

figure_4b

asn_TM_connected_1 <- 
  author_network |> 
  activate(nodes) |>
  dplyr::mutate(community = as.numeric(community)) |> 
  # filter(community >= 6) |> 
  dplyr::filter(community == 1) |> 
  # group_by(community) |> 
  dplyr::mutate(degree_community = centrality_degree()) |> 
  dplyr::arrange(desc(degree_community)) |> 
  dplyr::slice(1:10)
asn_TM_connected_2 <- 
  author_network |> 
  activate(nodes) |>
  dplyr::mutate(community = as.numeric(community)) |> 
  # filter(community >= 6) |> 
  dplyr::filter(community == 2) |> 
  # group_by(community) |> 
  dplyr::mutate(degree_community = centrality_degree()) |> 
  dplyr::arrange(desc(degree_community))|> 
  dplyr::slice(1:10)
asn_TM_connected_3 <- 
  author_network |> 
  activate(nodes) |>
  dplyr::mutate(community = as.numeric(community)) |> 
  # filter(community >= 6) |> 
  dplyr::filter(community == 3) |> 
  # group_by(community) |> 
  dplyr::mutate(degree_community = centrality_degree()) |> 
  dplyr::arrange(desc(degree_community)) |> 
  dplyr::slice(1:10)
asn_TM_connected_4 <- 
  author_network |> 
  activate(nodes) |>
  dplyr::mutate(community = as.numeric(community)) |> 
  # filter(community >= 6) |> 
  dplyr::filter(community == 4) |> 
  # group_by(community) |> 
  dplyr::mutate(degree_community = centrality_degree()) |> 
  dplyr::arrange(desc(degree_community)) |> 
  dplyr::slice(1:10)
asn_TM_connected_5 <- 
  author_network |> 
  activate(nodes) |>
  dplyr::mutate(community = as.numeric(community)) |> 
  # filter(community >= 6) |> 
  dplyr::filter(community == 5) |> 
  # group_by(community) |> 
  dplyr::mutate(degree_community = centrality_degree()) |> 
  dplyr::arrange(desc(degree_community)) |> 
  dplyr::slice(1:10)
asn_TM_connected_6 <- 
  author_network |> 
  activate(nodes) |>
  dplyr::mutate(community = as.numeric(community)) |> 
  # filter(community >= 6) |> 
  dplyr::filter(community == 6) |> 
  # group_by(community) |> 
  dplyr::mutate(degree_community = centrality_degree()) |> 
  dplyr::arrange(desc(degree_community)) |> 
  dplyr::slice(1:10)

nodes_community_1 <- 
  asn_TM_connected_1 |> 
  activate(nodes) |> 
  as_tibble() |> 
  dplyr::select(name)
nodes_community_2 <- 
  asn_TM_connected_2 |> 
  activate(nodes) |> 
  as_tibble() |> 
  dplyr::select(name)
nodes_community_3 <- 
  asn_TM_connected_3 |> 
  activate(nodes) |> 
  as_tibble() |> 
  dplyr::select(name)
# nodes_community_4 <- 
#   asn_TM_connected_4 |> 
#   activate(nodes) |> 
#   as_tibble() |> 
#   dplyr::select(name)
# nodes_community_5 <- 
#   asn_TM_connected_5 |> 
#   activate(nodes) |> 
#   as_tibble() |> 
#   dplyr::select(name)
# nodes_community_6 <- 
#   asn_TM_connected_6 |> 
#   activate(nodes) |> 
#   as_tibble() |> 
#   dplyr::select(name)
nodes_selected_10 <- 
  nodes_community_1 |> 
  bind_rows(nodes_community_2, 
            nodes_community_3,
            # nodes_community_4,
            # nodes_community_5,
            # nodes_community_6
  )

asn_selected_nodes <- 
  author_network |> 
  activate(nodes) |> 
  dplyr::filter(name %in% nodes_selected_10$name)  |> 
  dplyr::mutate(degree = centrality_degree())

# dplyr::mutate(final_plot = tidygraph::group_components(type = "weak")) |> 
# dplyr::filter(final_plot == 1)

figure_4c <- 
  asn_selected_nodes |> 
  ggraph(layout = "graphopt") +
  geom_edge_link(width = 1, 
                 colour = "lightgray") +
  geom_node_point(aes(color = community, 
                      size = degree)) +
  geom_node_text(aes(label = name), repel = TRUE) +
  theme_graph()

figure_4c

egos  <- 
  tidygraph::as_tbl_graph(x = AU_ego_edges) %>% 
  tidygraph::activate(nodes) %>% 
  dplyr::left_join(AU_ego_nodes %>% 
                     mutate(id = as.character(id)), 
                   by = c("name" = "id")) %>% 
  dplyr::mutate(component = as.character(component))


egos |>
  ggraph(layout = "graphopt") +
  geom_edge_link(aes(width = weight),
                 colour = "lightgray") +
  scale_edge_width(name = "Link strength") +
  geom_node_point(aes(color = component, 
                      size = degree)) +
  geom_node_text(aes(label = Label), repel = TRUE) +
  scale_size(name = "Degree") +
  # scale_color_binned(name = "Communities") +
  theme_graph()