#dùng phím tắt Ctrl + Alt + I để chèn chunk
lung_cancer_data <- data.frame(
  Method = c("Overall", "Endobronchial tumor", "Biopsy at endobronchial tumor site"),
  Diagnosis_Rate = c(38.55, 51.06, 63.33)
)
library(ggplot2)
library(ggthemes)
# Vẽ biểu đồ cột
ggplot(lung_cancer_data, aes(x = reorder(Method, Diagnosis_Rate), y = Diagnosis_Rate, fill = Method)) +
  geom_bar(stat = "identity", width = 0.2) +  # Thu nhỏ cột
  geom_text(aes(label = Diagnosis_Rate), vjust = -0.5, size = 5) +  # Hiển thị giá trị trên cột
  scale_fill_manual(values = c("#1E90FF", "#FF4500", "#2E8B57")) +  # Chọn màu phù hợp với slide
  labs(title = "Lung Cancer Diagnosis Rate",
       x = "Diagnosis Method",
       y = "Percentage (%)") +
  theme_minimal() +
  theme(legend.position = "none",  # Ẩn chú thích
        text = element_text(size = 14),
        axis.text.x = element_text(angle = 30, hjust = 1)) + # Xoay nhãn trục X cho dễ đọc
    ylim(0, 70) +
  labs(title = "",
       x = "",
       y = "Percentage of lung cancer diagnosis (%)") +
  theme_economist() +
  theme(legend.position = "none")  # Ẩn chú thích vì màu sắc đã phân biệt trên cột

ggsave("ten_file.png", width = 8, height = 4, dpi = 300)
# Create a dataframe with the data
symptom_data <- data.frame(
  Symptom = c("Dry cough", "Hemoptysis", "Productive cough", "Chest pain", "Dyspnea", 
              "Hoarseness", "Dysphagia", "Palpable peripheral lymph nodes"),
  
  UTP_Frequency = c(6, 8, 19, 22, 27, 2, 2, 6),
  UTP_Percentage = c(16.22, 21.62, 51.35, 59.46, 72.97, 5.41, 5.41, 16.22),

  Overall_Frequency = c(13, 15, 54, 47, 57, 3, 2, 9),
  Overall_Percentage = c(13.54, 15.63, 56.25, 48.96, 59.38, 3.13, 2.08, 9.38)
)

# Display the data
print(symptom_data)
##                           Symptom UTP_Frequency UTP_Percentage
## 1                       Dry cough             6          16.22
## 2                      Hemoptysis             8          21.62
## 3                Productive cough            19          51.35
## 4                      Chest pain            22          59.46
## 5                         Dyspnea            27          72.97
## 6                      Hoarseness             2           5.41
## 7                       Dysphagia             2           5.41
## 8 Palpable peripheral lymph nodes             6          16.22
##   Overall_Frequency Overall_Percentage
## 1                13              13.54
## 2                15              15.63
## 3                54              56.25
## 4                47              48.96
## 5                57              59.38
## 6                 3               3.13
## 7                 2               2.08
## 8                 9               9.38
# Create a dataframe with the data
symptom_data <- data.frame(
  Symptom = c("Dry cough", "Hemoptysis", "Productive cough", "Chest pain", "Dyspnea", 
              "Hoarseness", "Dysphagia", "Palpable peripheral lymph nodes"),
  
  UTP_Frequency = c(6, 8, 19, 22, 27, 2, 2, 6),
  UTP_Percentage = c(16.22, 21.62, 51.35, 59.46, 72.97, 5.41, 5.41, 16.22),

  Overall_Frequency = c(13, 15, 54, 47, 57, 3, 2, 9),
  Overall_Percentage = c(13.54, 15.63, 56.25, 48.96, 59.38, 3.13, 2.08, 9.38)
)

# Display the data
print(symptom_data)
##                           Symptom UTP_Frequency UTP_Percentage
## 1                       Dry cough             6          16.22
## 2                      Hemoptysis             8          21.62
## 3                Productive cough            19          51.35
## 4                      Chest pain            22          59.46
## 5                         Dyspnea            27          72.97
## 6                      Hoarseness             2           5.41
## 7                       Dysphagia             2           5.41
## 8 Palpable peripheral lymph nodes             6          16.22
##   Overall_Frequency Overall_Percentage
## 1                13              13.54
## 2                15              15.63
## 3                54              56.25
## 4                47              48.96
## 5                57              59.38
## 6                 3               3.13
## 7                 2               2.08
## 8                 9               9.38
# Load necessary library
library(ggplot2)
library(reshape2)

# Create the dataframe with percentages
symptom_data <- data.frame(
  Symptom = c("Dry cough", "Hemoptysis", "Productive cough", "Chest pain", "Dyspnea", 
              "Hoarseness", "Dysphagia", "Palpable lymph nodes"),
  
  UTP_Percentage = c(16.22, 21.62, 51.35, 59.46, 72.97, 5.41, 5.41, 16.22),
  Overall_Percentage = c(13.54, 15.63, 56.25, 48.96, 59.38, 3.13, 2.08, 9.38)
)

# Convert data to long format for ggplot
symptom_long <- melt(symptom_data, id.vars = "Symptom", 
                     variable.name = "Group", value.name = "Percentage")

# Create the bar chart with percentages
ggplot(symptom_long, aes(x = reorder(Symptom, Percentage), y = Percentage, fill = Group)) +
  geom_bar(stat = "identity", position = "dodge", width = 0.8) +  # Dodge bars for comparison
  geom_text(aes(label = paste0(Percentage, "%")), vjust = -0.4, size = 4, 
            position = position_dodge(0.8)) +  # Reduce text size on bars
  scale_fill_manual(values = c("#1E90FF", "#FF4500"), labels = c("Lung cancer Group(N=37)", "Overall Group(N=96)")) +  # Set colors
  labs(title = "Symptoms",
       x = "Symptoms",
       y = "Percentage (%)",
       fill = "Group") +
  theme_economist() +
  theme(axis.text.x = element_text(hjust = 1, size = 8),  # Reduce text size of x-axis labels
        axis.title = element_text(size = 8),  # Adjust axis title size
        legend.text = element_text(size = 8),  # Adjust legend text size
        legend.title = element_text(size = 8),
        text = element_text(size = 10))  # Adjust general text size

  ggsave("symptom.png", width = 10, height = 6, dpi = 300)      
# Load necessary libraries
library(ggplot2)
library(reshape2)

# Create the dataframe with percentages
clinical_data <- data.frame(
  Clinical_Feature = c("Triad of decreased signs", 
                       "Lower airway obstruction syndrome", 
                       "Mediastinal syndrome", 
                       "Respiratory tract infection syndrome", 
                       "Not recorded"),
  
  LC_Percentage = c(32.43, 37.84, 10.81, 21.62, 16.22),
  Overall_Percentage = c(22.92, 23.96, 6.25, 38.54, 16.67)
)

# Convert data to long format for ggplot
clinical_long <- melt(clinical_data, id.vars = "Clinical_Feature", 
                      variable.name = "Group", value.name = "Percentage")
# Load necessary libraries
library(ggplot2)
library(reshape2)

# Create the dataframe with percentages
clinical_data <- data.frame(
  Clinical_Feature = c("Triad of decreased signs", 
                       "Lower airway obstruction syndrome", 
                       "Mediastinal syndrome", 
                       "Respiratory tract infection syndrome", 
                       "Not recorded"),  # Đưa cột này xuống cuối
  
  UTP_Percentage = c(32.43, 37.84, 10.81, 21.62, 16.22),
  Overall_Percentage = c(22.92, 23.96, 6.25, 38.54, 16.67)
)

# Convert data to long format for ggplot
clinical_long <- melt(clinical_data, id.vars = "Clinical_Feature", 
                      variable.name = "Group", value.name = "Percentage")

# Factor to set the order manually (đảm bảo "Not recorded" ở ngoài cùng bên phải)
clinical_long$Clinical_Feature <- factor(clinical_long$Clinical_Feature, 
                                         levels = c("Triad of decreased signs", 
                                                    "Lower airway obstruction syndrome", 
                                                    "Mediastinal syndrome", 
                                                    "Respiratory tract infection syndrome", 
                                                    "Not recorded"))  # "Not recorded" ở cuối

# Create the bar chart
ggplot(clinical_long, aes(x = Clinical_Feature, y = Percentage, fill = Group)) +
  geom_bar(stat = "identity", position = "dodge", width = 0.7) +  # Dodge bars for comparison
  geom_text(aes(label = paste0(Percentage, "%")), vjust = -0.3, size = 4, 
            position = position_dodge(0.7)) +  # Reduce text size on bars
  scale_fill_manual(values = c("#1E90FF", "#FF4500"), labels = c("Lung cancer (N=37)", "Overall (N=96)"))+
  labs(title = "Signs",
       x = "",
       y = "Percentage (%)",
       fill = "Group") +
  theme_economist() +
  theme(axis.text.x = element_text(angle = 0, hjust = 0.5, size = 10),  # Keep X-axis labels horizontal
        axis.title = element_text(size = 12),  # Adjust axis title size
        legend.text = element_text(size = 10),  # Adjust legend text size
        legend.title = element_text(size = 12),
        text = element_text(size = 12))  # Adjust general text size

  ggsave("sign.png", width = 14, height = 6, dpi = 300)