Mini Project

Question 1

data(cars)
summary(cars)

Question 2

install.packages("jsonlite")
library(jsonlite)
BTC <- fromJSON("https://min-api.cryptocompare.com/data/v2/histoday?fsym=BTC&tsym=USD&limit=100")

str(BTC)

BTC_data <- BTC$Data$Data  

head(BTC_data)

max_close_price <- max(BTC_data$close, na.rm = TRUE)

max_close_price

Question 3

Identify a topic of interest and give your project a name/title.

Community health in relation to patient satisfaction and quality of life

Phrase 3-5 research questions you would like to explore.

1. How does health service type (rehab, preventive, consultation) relate to patient satisfaction and quality of life scores?

2. What is the relationship between visit frequency and patient satisfaction?

3. What biomechanical characteristics are most strongly associated with high EMG activity levels?

List the data sources that you find that are relevant with your research questions.

https://www.kaggle.com/datasets/ziya07/community-health-evaluation-dataset

Extract one or more relevant datasets associate with your research questions, either import the downloaded dataset(s), extract from APIs, or ethically scrape the web, etc.

library(readr)
community_health_data <- read_csv("~/Downloads/community_health_evaluation_dataset.csv")

Rows: 347 Columns: 12── Column specification ─────────────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (4): Gender, Service Type, Visit Frequency, EMG Activity
dbl (8): Participant ID, Age, SES, Step Frequency (steps/min), Stride Length (m), Joint Angle (°)...
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

View(community_health_data)

Describe your data extracted, statistically and/or visually.

The Community Health Evaluation Dataset contains synthesized data on 347 participants, capturing demographic details, healthcare usage patterns, and biomechanical metrics to assess community health services and quality. It includes variables such as age, socioeconomic status, visit frequency, stride length, joint angles, and patient satisfaction, aimed at understanding relationships between biomechanical health indicators and quality of life.

colnames(community_health_data) <- c("Participant_ID", "Age", "Gender", "SES", "Service_Type",
                                     "Visit_Frequency", "Step_Frequency", "Stride_Length",
                                     "Joint_Angle", "EMG_Activity", "Patient_Satisfaction",
                                     "Quality_of_Life_Score")

library(ggplot2)
ggplot(community_health_data, aes(x = Visit_Frequency, y = Patient_Satisfaction, fill = Visit_Frequency)) +
  geom_boxplot(outlier.color = "red", outlier.shape = 16, outlier.size = 2) +
  labs(title = "Relationship between Visit Frequency and Patient Satisfaction",
       x = "Visit Frequency",
       y = "Patient Satisfaction") +
  theme_minimal() +
  theme(legend.position = "none")

Key observations:

Weekly visits have the highest median satisfaction score, as represented by the middle line in the box, which is above 7.

Yearly and Monthly visits have lower median satisfaction scores, hovering around 5, with the Monthly group showing slightly more variation in satisfaction.

The spread (interquartile range) of satisfaction scores is largest for the “Weekly” group, indicating that weekly visitors reported a wider range of satisfaction.

Outliers are not shown in this plot, but the whiskers indicate the range of the data within 1.5 times the interquartile range from the quartiles.

library(ggplot2)
ggplot(community_health_data, aes(x = Service_Type, y = Patient_Satisfaction, fill = Service_Type)) +
  geom_boxplot(outlier.color = "red", outlier.shape = 16, outlier.size = 2) + # Outliers are marked in red
  labs(title = "Patient Satisfaction by Health Service Type",
       x = "Health Service Type",
       y = "Patient Satisfaction (1-10)") +
  theme_minimal() +
  theme(legend.position = "none")

Key Observations:

Median Satisfaction Scores: All three health service types (Consultation, Preventive, and Rehab) have similar median patient satisfaction scores, centered around 5. This suggests that the typical satisfaction level is consistent across these service types.

Variation in Satisfaction: The Consultation and Rehab services have wider interquartile ranges (IQRs) compared to Preventive services, indicating that patient satisfaction is more varied in these two categories. Specifically, patients receiving Consultation or Rehab services reported a broader range of satisfaction levels.

Outliers and Extremes: None of the service types show extreme outliers in patient satisfaction, but the Consultation service has the lowest satisfaction score (around 2.5), while the Preventive and Rehab services have a slightly more concentrated distribution around the median. This could suggest that Consultation services may have more room for improvement in terms of patient satisfaction.

Perform necessary data cleaning and manipulation especially if the raw data contains special values or not directly in the format that can answer your research questions.

missing_values <- colSums(is.na(community_health_data))

missing_values <- missing_values[missing_values > 0]

print("Columns with missing values and their counts:")
print(missing_values)

no missing values

List future data preparation work needed if any.

continuing to segment the data to make correlations more visable.