myawesomepkg 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

myawesomepkg/TSAPY1/9A_Dplyr.py

@@ -0,0 +1,85 @@
+✅ Step 1: Load dplyr
+r
+Copy
+Edit
+library(dplyr)
+🔹 Sample Data
+r
+Copy
+Edit
+employees <- data.frame(
+  emp_id = c(1, 2, 3, 4, 5),
+  name = c("John", "Emma", "Raj", "Sara", "Mike"),
+  dept_id = c(10, 20, 10, 30, 20)
+)
+
+departments <- data.frame(
+  dept_id = c(10, 20, 30),
+  dept_name = c("HR", "Finance", "IT")
+)
+🔹 1. Filtering Rows
+r
+Copy
+Edit
+# Filter employees from dept 10
+employees %>% 
+  filter(dept_id == 10)
+🔹 2. Mutating Joins (left_join)
+r
+Copy
+Edit
+# Add department name to employees
+employees %>%
+  left_join(departments, by = "dept_id")
+🔹 3. Inner Join
+r
+Copy
+Edit
+# Only matching employees with department info
+employees %>%
+  inner_join(departments, by = "dept_id")
+🔹 4. Handling Duplicate Keys
+r
+Copy
+Edit
+# Add a duplicate dept row
+departments2 <- rbind(departments, data.frame(dept_id = 10, dept_name = "HR-Duplicate"))
+
+# Join - will create multiple rows for duplicate keys
+employees %>%
+  left_join(departments2, by = "dept_id")
+🔹 5. Defining Key Column (custom join keys)
+r
+Copy
+Edit
+emp <- data.frame(id = c(1, 2), val = c("A", "B"))
+ref <- data.frame(key = c(1, 2), desc = c("X", "Y"))
+
+emp %>% 
+  left_join(ref, by = c("id" = "key"))
+🔹 6. Filtering Joins
+r
+Copy
+Edit
+# Semi Join: Keep rows in employees that match departments
+employees %>% 
+  semi_join(departments, by = "dept_id")
+
+# Anti Join: Keep rows in employees that don't match departments
+employees %>% 
+  anti_join(departments, by = "dept_id")
+🔹 7. Set Operations
+r
+Copy
+Edit
+a <- data.frame(x = c(1, 2, 3))
+b <- data.frame(x = c(2, 3, 4))
+
+# Union (unique values)
+union(a, b)
+
+# Intersect (common values)
+intersect(a, b)
+
+# Set difference (in a but not in b)
+setdiff(a, b)

myawesomepkg/TSAPY1/9B_Tidyr.py

@@ -0,0 +1,71 @@
+✅ Step 1: Load tidyr and dplyr
+r
+Copy
+Edit
+library(tidyr)
+library(dplyr)
+🔹 Sample Data
+r
+Copy
+Edit
+data <- data.frame(
+  name = c("Alice", "Bob"),
+  math = c(90, 85),
+  science = c(95, 80)
+)
+🔹 1. Gathering → pivot_longer()
+r
+Copy
+Edit
+data_long <- data %>%
+  pivot_longer(cols = c(math, science), names_to = "subject", values_to = "score")
+
+print(data_long)
+🔹 2. Spreading → pivot_wider()
+r
+Copy
+Edit
+data_wide <- data_long %>%
+  pivot_wider(names_from = subject, values_from = score)
+
+print(data_wide)
+🔹 3. Separate Columns
+r
+Copy
+Edit
+full_name <- data.frame(name = c("Alice_Smith", "Bob_Jones"))
+
+# Separate name into first and last
+full_name_sep <- full_name %>%
+  separate(name, into = c("first_name", "last_name"), sep = "_")
+
+print(full_name_sep)
+🔹 4. Unite Columns
+r
+Copy
+Edit
+# Combine first_name and last_name
+full_name_united <- full_name_sep %>%
+  unite("full_name", first_name, last_name, sep = " ")
+
+print(full_name_united)
+🔹 5. Handling Missing Values
+r
+Copy
+Edit
+missing_data <- data.frame(
+  name = c("A", "B", "C"),
+  score = c(85, NA, 90)
+)
+
+# Remove rows with NA
+missing_data_clean <- missing_data %>%
+  drop_na()
+
+# Replace NA with value
+missing_data_filled <- missing_data %>%
+  replace_na(list(score = 0))
+
+print(missing_data_clean)
+print(missing_data_filled)
+Let m