---
title: "My Fitness Journey: Understanding Calorie Burn Patterns"
author: "Nehasingh Rajput"
date: "`r Sys.Date()`"
output: 
  flexdashboard::flex_dashboard:
    orientation: columns
    vertical_layout: fill
    theme: cosmo
    storyboard: true
    social: menu
    source: embed
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = FALSE, warning = FALSE, message = FALSE)

# Load required libraries
if (!require("pacman")) install.packages("pacman")
pacman::p_load(
  flexdashboard, plotly, DT, viridis, scales, 
  corrplot, tidyverse, ggplot2, dplyr, 
  lubridate, RColorBrewer, gridExtra
)

# Load and prepare data
calories <- read.csv("D:/data/calories.csv")  # Change this to your file path

# Enhanced data processing
calories_enhanced <- calories %>%
  mutate(
    # Create meaningful categories
    BMI = Weight / ((Height/100)^2),
    BMI_Category = case_when(
      BMI < 18.5 ~ "Underweight",
      BMI < 25 ~ "Normal",
      BMI < 30 ~ "Overweight",
      TRUE ~ "Obese"
    ),
    Age_Group = case_when(
      Age < 25 ~ "Young (18-24)",
      Age < 35 ~ "Adult (25-34)", 
      Age < 45 ~ "Middle-aged (35-44)",
      Age < 55 ~ "Mature (45-54)",
      TRUE ~ "Senior (55+)"
    ),
    Duration_Category = case_when(
      Duration < 15 ~ "Short (<15 min)",
      Duration < 30 ~ "Medium (15-30 min)",
      Duration < 45 ~ "Long (30-45 min)",
      TRUE ~ "Extended (45+ min)"
    ),
    Intensity = case_when(
      Heart_Rate < 100 ~ "Low Intensity",
      Heart_Rate < 140 ~ "Moderate Intensity",
      Heart_Rate < 170 ~ "High Intensity",
      TRUE ~ "Maximum Intensity"
    ),
    Calories_per_Minute = Calories / Duration,
    Heart_Rate_Zone = case_when(
      Heart_Rate < 114 ~ "Fat Burn Zone",
      Heart_Rate < 133 ~ "Aerobic Zone", 
      Heart_Rate < 152 ~ "Anaerobic Zone",
      TRUE ~ "Red Line Zone"
    )
  ) %>%
  # Remove any potential outliers
  filter(
    Duration > 0,
    Calories > 0,
    Heart_Rate > 60 & Heart_Rate < 200,
    Body_Temp > 36 & Body_Temp < 42
  )

# Color schemes based on design principles
fitness_colors <- c(
  "Male" = "#3498db",
  "Female" = "#e74c3c",
  "Low Intensity" = "#2ecc71",
  "Moderate Intensity" = "#f39c12", 
  "High Intensity" = "#e74c3c",
  "Maximum Intensity" = "#8e44ad"
)

# Custom theme
theme_fitness <- theme_minimal() +
  theme(
    plot.title = element_text(size = 14, face = "bold"),
    plot.subtitle = element_text(size = 11, color = "gray60"),
    legend.position = "bottom",
    panel.grid.minor = element_blank(),
    strip.text = element_text(face = "bold")
  )
```

### Project Overview {data-commentary-width=400}

```{r overview-kpis}
# Key Performance Indicators
total_workouts <- nrow(calories_enhanced)
avg_calories <- round(mean(calories_enhanced$Calories), 1)
avg_duration <- round(mean(calories_enhanced$Duration), 1)
avg_heart_rate <- round(mean(calories_enhanced$Heart_Rate), 0)

# Create summary table
kpi_summary <- data.frame(
  Metric = c("Total Workouts", "Avg Calories Burned", "Avg Duration (min)", "Avg Heart Rate (bpm)"),
  Value = c(paste(total_workouts), paste(avg_calories), paste(avg_duration), paste(avg_heart_rate)),
  stringsAsFactors = FALSE
)

knitr::kable(kpi_summary, 
             caption = "Fitness Overview - Key Metrics",
             col.names = c("Metric", "Value"))
```

***

**Research Questions:**

This fitness dashboard analyzes workout data to answer five key questions:

1. **Efficiency Question**: What factors most strongly predict calorie burn during workouts?

2. **Optimization Question**: Which workout duration and intensity combinations are most effective for calorie burning?

3. **Demographic Question**: How do calorie burn patterns differ between age groups and genders?

4. **Performance Question**: What heart rate zones lead to optimal calorie burn rates?

5. **Health Question**: How does BMI category relate to workout intensity and calorie burn efficiency?

**Data Collection Methods:**
- Dataset contains 15,000 workout sessions from fitness trackers
- Variables include demographics, workout metrics, and physiological data
- Data cleaned to remove outliers and ensure quality

**Visualization Methods:**
- Interactive charts using plotly for exploration
- Color coding based on visual perception principles
- Multiple chart types optimized for different data comparisons

### Q1: Calorie Burn Predictors {data-commentary-width=350}

```{r correlation-analysis, fig.height=6, fig.width=10}
# Correlation analysis
numeric_vars <- calories_enhanced %>%
  select(Age, Height, Weight, Duration, Heart_Rate, Body_Temp, Calories, BMI, Calories_per_Minute)

correlation_matrix <- cor(numeric_vars, use = "complete.obs")

# Create interactive correlation plot
# Convert correlation matrix to long format for ggplot
cor_long <- correlation_matrix %>%
  as.data.frame() %>%
  rownames_to_column("var1") %>%
  pivot_longer(-var1, names_to = "var2", values_to = "correlation") %>%
  mutate(
    correlation_text = round(correlation, 3),
    correlation_abs = abs(correlation)
  )

cor_plot <- ggplot(cor_long, aes(x = var1, y = var2, fill = correlation)) +
  geom_tile(color = "white") +
  geom_text(aes(label = correlation_text), color = "white", size = 3) +
  scale_fill_gradient2(low = "#3498db", mid = "white", high = "#e74c3c",
                       midpoint = 0, limit = c(-1,1), space = "Lab",
                       name = "Correlation") +
  labs(title = "Correlation Matrix: Factors Affecting Calorie Burn",
       subtitle = "Darker colors indicate stronger relationships",
       x = "", y = "") +
  theme_fitness +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

ggplotly(cor_plot, tooltip = c("x", "y", "fill"))
```

***

**Key Findings:**

Based on the correlation analysis:

- **Duration** shows the strongest relationship with calories burned
- **Weight** has a strong positive correlation with calorie burn
- **Heart Rate** shows moderate correlation with calories
- **Age** shows minimal impact on workout performance

**Insight**: Workout duration and body weight are the primary predictors of calorie burn, while age has surprisingly little effect on performance.

### Q2: Duration vs Intensity Optimization {data-commentary-width=350}

```{r efficiency-analysis, fig.height=6, fig.width=10}
# Scatter plot of duration vs calories with intensity zones
efficiency_plot <- calories_enhanced %>%
  ggplot(aes(x = Duration, y = Calories, color = Intensity)) +
  geom_point(alpha = 0.6, size = 1.5) +
  geom_smooth(method = "lm", se = FALSE, size = 1.2) +
  facet_wrap(~Intensity, scales = "free") +
  scale_color_manual(values = c("Low Intensity" = "#2ecc71",
                               "Moderate Intensity" = "#f39c12", 
                               "High Intensity" = "#e74c3c",
                               "Maximum Intensity" = "#8e44ad")) +
  labs(title = "Workout Efficiency: Duration vs Calorie Burn by Intensity",
       subtitle = "Each panel shows different intensity levels",
       x = "Duration (minutes)", 
       y = "Calories Burned",
       color = "Intensity Level") +
  theme_fitness

ggplotly(efficiency_plot, tooltip = c("x", "y", "colour"))
```

***

**Optimization Insights:**

From the duration vs. intensity analysis:

- **Higher intensity** workouts show steeper calorie burn slopes
- **Moderate intensity** provides good balance of sustainability and effectiveness  
- **Linear relationships** are clear across all intensity levels
- **Time investment** remains crucial regardless of intensity

**Recommendation**: Focus on consistency and gradually increasing duration before maximizing intensity.

### Q3: Demographics and Performance {data-commentary-width=350}

```{r demographics-analysis, fig.height=8, fig.width=12}
# Box plots by age group and gender
demo_plot <- calories_enhanced %>%
  ggplot(aes(x = Age_Group, y = Calories_per_Minute, fill = Gender)) +
  geom_boxplot(alpha = 0.8, outlier.alpha = 0.3) +
  scale_fill_manual(values = c("male" = "#3498db", "female" = "#e74c3c")) +
  labs(title = "Calorie Burn Rate by Demographics",
       subtitle = "Calories burned per minute of exercise",
       x = "Age Group", 
       y = "Calories per Minute",
       fill = "Gender") +
  theme_fitness +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

# Add statistical summary
demo_interactive <- ggplotly(demo_plot, tooltip = c("x", "y", "fill"))

demo_interactive
```

***

**Demographic Patterns:**

The analysis reveals:

- **Gender differences** exist but with substantial overlap
- **Age groups** show varying performance patterns
- **Individual variation** is significant within each demographic
- **Senior participants** often perform better than expected

**Insight**: Demographics provide context but individual effort and consistency matter more than age or gender for fitness outcomes.

### Q4: Heart Rate Zone Analysis {data-commentary-width=350}

```{r heart-rate-analysis, fig.height=6, fig.width=10}
# Heart rate zones and calorie efficiency
hr_analysis <- calories_enhanced %>%
  group_by(Heart_Rate_Zone, Duration_Category) %>%
  summarise(
    avg_calories_per_min = mean(Calories_per_Minute),
    count = n(),
    .groups = "drop"
  ) %>%
  filter(count >= 50)  # Only include combinations with sufficient data

hr_plot <- hr_analysis %>%
  ggplot(aes(x = Duration_Category, y = avg_calories_per_min, 
             fill = Heart_Rate_Zone, size = count)) +
  geom_col(position = "dodge", alpha = 0.8) +
  scale_fill_viridis_d(option = "plasma", name = "Heart Rate Zone") +
  labs(title = "Calorie Burn Efficiency by Heart Rate Zone and Duration",
       subtitle = "Average calories burned per minute",
       x = "Workout Duration Category", 
       y = "Calories per Minute",
       size = "Number of Workouts") +
  theme_fitness +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

ggplotly(hr_plot, tooltip = c("x", "y", "fill", "size"))
```

***

**Heart Rate Zone Insights:**

The heart rate analysis shows:

- **Aerobic Zone** often provides excellent calorie burn efficiency
- **Different zones** work better for different workout durations
- **Sustainability** matters for longer sessions
- **Zone selection** should match fitness goals and time availability

**Training Recommendation**: Focus primarily on sustainable heart rate zones that you can maintain for your preferred workout duration.

### Q5: BMI and Workout Patterns {data-commentary-width=350}

```{r bmi-analysis, fig.height=8, fig.width=10}
# BMI analysis with multiple metrics
bmi_summary <- calories_enhanced %>%
  filter(BMI_Category %in% c("Normal", "Overweight")) %>%  # Focus on main categories
  group_by(BMI_Category, Intensity) %>%
  summarise(
    avg_calories = mean(Calories),
    avg_duration = mean(Duration),
    avg_efficiency = mean(Calories_per_Minute),
    count = n(),
    .groups = "drop"
  ) %>%
  filter(count >= 100)  # Ensure sufficient sample size

# Create comparison chart
bmi_plot <- bmi_summary %>%
  ggplot(aes(x = BMI_Category, y = avg_calories, fill = Intensity)) +
  geom_col(position = "dodge", alpha = 0.8) +
  scale_fill_manual(values = c("Low Intensity" = "#2ecc71",
                              "Moderate Intensity" = "#f39c12", 
                              "High Intensity" = "#e74c3c",
                              "Maximum Intensity" = "#8e44ad")) +
  labs(title = "Average Calories Burned by BMI Category",
       subtitle = "Breakdown by workout intensity level",
       x = "BMI Category", 
       y = "Average Calories per Session",
       fill = "Intensity Level") +
  theme_fitness +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

ggplotly(bmi_plot, tooltip = c("x", "y", "fill"))
```

***

**BMI and Performance Patterns:**

The BMI analysis reveals:

- **Higher BMI individuals** tend to burn more total calories per session
- **All BMI categories** can successfully engage in various intensity levels
- **Workout intensity preferences** vary but moderate intensity is popular across groups
- **Individual variation** exists within each BMI category

**Health Insight**: BMI category doesn't limit workout potential - focus should be on finding sustainable routines rather than comparing absolute numbers across weight categories.

### Data Summary and Methodology {data-commentary-width=400}

```{r data-summary}
# Data quality summary
sample_data <- calories_enhanced %>%
  select(User_ID, Gender, Age, BMI, Duration, Heart_Rate, Calories, Intensity, BMI_Category) %>%
  sample_n(min(100, nrow(calories_enhanced)))

DT::datatable(
  sample_data,
  options = list(pageLength = 10, scrollX = TRUE),
  caption = "Sample of Processed Fitness Data"
) %>%
  DT::formatRound(columns = c("BMI"), digits = 1)
```

***

**Data Collection and Processing:**

**Original Dataset:**
- 15,000 workout sessions from fitness trackers
- 9 variables including demographics and workout metrics
- Data spans multiple users and workout types

**Data Enhancement:**
- Calculated BMI and categorized into health ranges
- Created intensity zones based on heart rate
- Derived efficiency metrics (calories per minute)
- Grouped continuous variables into meaningful categories

**Visualization Methods:**
- Interactive charts using plotly for exploration
- Color coding follows visual perception principles
- Multiple chart types optimized for different comparisons
- Consistent theme and professional styling

**Key Insights Summary:**
1. **Duration and weight** are the strongest predictors of calorie burn
2. **Moderate intensity** provides good balance of effectiveness and sustainability
3. **Age is less limiting** than commonly assumed for fitness performance
4. **Heart rate zones** can be optimized based on workout duration goals
5. **BMI affects total calories** but doesn't limit workout intensity potential

**Limitations:**
- Data represents point-in-time snapshots, not longitudinal tracking
- Individual metabolic differences not captured
- Workout types (running, cycling, etc.) not specified
- Environmental factors (temperature, humidity) not included

**Future Analysis Opportunities:**
- Longitudinal tracking to show improvement over time
- Workout type classification and comparison
- Seasonal patterns and environmental factors
- Personalized recommendations based on individual baselines

**Conclusion:**
This analysis demonstrates that effective fitness is achievable across all demographics through consistent, appropriately-intensified exercise. The key is finding sustainable routines that match individual capabilities and preferences rather than pursuing maximum intensity at all costs.