Julia DataFrames & Data Science

Work with tabular data using DataFrames.jl.

Creating DataFrames

using DataFrames

# From vectors
df = DataFrame(
    name = ["Alice", "Bob", "Charlie"],
    age = [25, 30, 35],
    score = [85.5, 92.0, 78.5]
)

# From dictionary
data = Dict(
    "name" => ["Alice", "Bob"],
    "age" => [25, 30]
)
df2 = DataFrame(data)

Basic Operations

# View first/last rows
first(df, 2)
last(df, 2)

# Get dimensions
size(df)  # (rows, columns)

# Column operations
df.age        # Access column
df[!, :age]   # Another way
df.score .+ 5 # Vectorized operation

Filtering and Subsetting

# Filter rows
filter(row -> row.age > 25, df)

# Using @subset macro
using DataFramesMeta
@subset(df, :age > 25, :score > 80)

# Select columns
select(df, [:name, :age])

Grouping and Aggregation

# Group by and summarize
using Statistics

gdf = groupby(df, :age)
combine(gdf, :score => mean)

# Using @chain macro
using Chain
@chain df begin
    groupby(:age)
    combine(:score => mean => :avg_score)
end

Reading/Writing Data

using CSV

# Read CSV
data = CSV.read("data.csv", DataFrame)

# Write CSV
CSV.write("output.csv", df)

Data Visualization

using Plots, StatsPlots

# Scatter plot
@df df scatter(:age, :score, group=:name)

# Histogram
@df df histogram(:score)

← Back to Tutorials