import pandas as pd

df = pd.DataFrame({
    "student": ["Asha", "Ravi", "Meera", "Kabir"],
    "course": ["Python", "Java", "Python", "Java"],
    "marks": [82, 74, 91, 68],
})
print(df[df["marks"] >= 75])
print(df.groupby("course")["marks"].mean())

public class Student {
    private final String name;
    private final String course;
    private final int marks;

    public Student(String name, String course, int marks) {
        this.name = name;
        this.course = course;
        this.marks = marks;
    }

    public boolean passed() { return marks >= 75; }
    public String getName() { return name; }
    public String getCourse() { return course; }
    public int getMarks() { return marks; }
}

import pandas as pd

# marks.csv:
# student,course,marks
# Asha,Python,82
# Ravi,Java,74
# Meera,Python,91
# Kabir,Java,68

df = pd.read_csv("marks.csv")
print(df.groupby("course")["marks"].mean().round(1))
# course
# Java      71.0
# Python    86.5

import java.nio.file.*;
import java.util.*;
import java.util.stream.*;

public class AverageMarks {
    record Row(String student, String course, int marks) {}

    public static void main(String[] args) throws Exception {
        List<Row> rows = Files.readAllLines(Path.of("marks.csv")).stream()
            .skip(1)                                   // header
            .map(line -> line.split(","))
            .map(p -> new Row(p[0], p[1], Integer.parseInt(p[2].trim())))
            .toList();

        Map<String, Double> avg = rows.stream()
            .collect(Collectors.groupingBy(Row::course, TreeMap::new,
                     Collectors.averagingInt(Row::marks)));
        avg.forEach((course, a) -> System.out.printf("%s %.1f%n", course, a));
        // Java 71.0
        // Python 86.5
    }
}

import pandas as pd
import numpy as np

df = pd.DataFrame({"price": np.random.randint(100, 5000, 1_000_000)})

# Slow: Python loop over rows
# df["gst"] = [p * 0.18 for p in df["price"]]

# Fast: vectorised column operation
df["gst"] = df["price"] * 0.18
print(df.head())

Data path (Python + pandas)
Python → pandas → SQL → visualisation → statistics → ML basics
Roles: data analyst, data scientist, analytics engineer

Software path (Java)
Java → OOP → collections → SQL/JDBC → Spring Boot → testing
Roles: Java developer, backend engineer, Android developer

Tick what you enjoy
☐ Finding patterns in sales or survey data   → pandas
☐ Building an app or API others use         → Java
☐ Making charts and reports                 → pandas
☐ Designing classes and system structure    → Java
More ticks decide your first path.

Pandas path
First month: Python basics
Second month: pandas — read, filter, group, merge, clean
Third month: SQL + one analysis project with charts

Java path
First month: Java syntax, OOP
Second month: Collections, exceptions, streams
Third month: SQL + a small Spring Boot API

Scan 20 posts for each path in your city
Data roles listing pandas/Python: ____
Java developer roles: ____
Entry-level friendly: data ____ / Java ____
Skills repeated most: ____