When working with large datasets, you often need to perform aggregations without loading the entire file into memory. One common task is to sum the values of a specific column in a very large CSV file. Since the file may not fit in memory, you can process it in manageable chunks using `pandas` `read_csv()` function with the `chunksize` parameter. 

For each chunk, you calculate the sum of the desired column, then aggregate these partial sums to get the total. This approach is efficient and scalable, allowing you to handle files of virtually any size as long as each chunk fits into memory.


import unittest
import user_code
import ast
import re   
import importlib
import csv
import unittest
import importlib
import os
import csv
import pandas as pd

class TestTask(unittest.TestCase):
    def setUp(self):
        # Create test CSV files for different scenarios
        self.one_chunk_file = "test_one_chunk.csv"
        self.multi_chunk_file = "test_multi_chunk.csv"
        self.float_file = "test_float.csv"
        self.empty_col_file = "test_empty_col.csv"
        self.no_col_file = "test_no_col.csv"

        # One chunk: 3 rows
        with open(self.one_chunk_file, "w", newline="") as f:
            writer = csv.writer(f)
            writer.writerow(["amount", "desc"])
            writer.writerow([10, "a"])
            writer.writerow([20, "b"])
            writer.writerow([30, "c"])
        # Multi chunk: 6 rows
        with open(self.multi_chunk_file, "w", newline="") as f:
            writer = csv.writer(f)
            writer.writerow(["value", "desc"])
            for i in range(1, 7):
                writer.writerow([i, f"row{i}"])
        # Float values
        with open(self.float_file, "w", newline="") as f:
            writer = csv.writer(f)
            writer.writerow(["price", "desc"])
            writer.writerow([1.5, "x"])
            writer.writerow([2.5, "y"])
            writer.writerow([3.0, "z"])
        # Empty column
        with open(self.empty_col_file, "w", newline="") as f:
            writer = csv.writer(f)
            writer.writerow(["col1", "col2"])
            writer.writerow(["", "a"])
            writer.writerow(["", "b"])
        # No such column
        with open(self.no_col_file, "w", newline="") as f:
            writer = csv.writer(f)
            writer.writerow(["foo", "bar"])
            writer.writerow([1, 2])
            writer.writerow([3, 4])

    def tearDown(self):
        for f in [self.one_chunk_file, self.multi_chunk_file, self.float_file, self.empty_col_file, self.no_col_file]:
            if os.path.exists(f):
                os.remove(f)

    def test_sum_one_chunk(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.sum_column_in_chunks(self.one_chunk_file, "amount", 100)
        _dynamic_test(
            self,
            result == 60,
            "Returns correct sum when file fits in one chunk.",
            f"Expected 60, got {result} for one chunk file."
        )

    def test_sum_multiple_chunks(self):
        import user_code
        importlib.reload(user_code)
        # chunksize=2, so 3 chunks
        result = user_code.sum_column_in_chunks(self.multi_chunk_file, "value", 2)
        _dynamic_test(
            self,
            result == 21,
            "Returns correct sum when file is read in multiple chunks.",
            f"Expected 21, got {result} for multi-chunk file."
        )

    def test_sum_float_column(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.sum_column_in_chunks(self.float_file, "price", 2)
        _dynamic_test(
            self,
            abs(result - 7.0) < 1e-8,
            "Returns correct sum for float column.",
            f"Expected 7.0, got {result} for float column."
        )

    def test_sum_empty_column(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.sum_column_in_chunks(self.empty_col_file, "col1", 1)
        _dynamic_test(
            self,
            result == 0,
            "Returns 0 for column with no values.",
            f"Expected 0, got {result} for empty column."
        )

    def test_sum_column_not_exist(self):
        import user_code
        importlib.reload(user_code)
        result = user_code.sum_column_in_chunks(self.no_col_file, "notacol", 1)
        _dynamic_test(
            self,
            result == 0,
            "Returns 0 if column does not exist.",
            f"Expected 0, got {result} for missing column."
        )

def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

def normalize_text(text):
    text = text.lower()
    text = re.sub(r"\\s{2,}", " ", text)
    text = re.sub(r"\\s*([,:?])\\s*", r"\\1 ", text)
    return text.strip()

def change_var(code: str, var_name: str, value: str) -> str:
    tree = ast.parse(code)
    lines = code.splitlines()
    changed = False
    # Collect all assignment nodes to modify
    assign_nodes = [
        (i, node)
        for i, node in enumerate(tree.body)
        if isinstance(node, ast.Assign)
        and any(isinstance(target, ast.Name) and target.id == var_name for target in node.targets)
    ]

    # If nothing to change, return unmodified code
    if not assign_nodes:
        return code

    # Perform replacements for all matching assignments (from last to first to not break line offsets)
    for i, node in reversed(assign_nodes):
        start_line = node.lineno - 1
        line = lines[start_line]
        indent = ' ' * (len(line) - len(line.lstrip()))
        lines[start_line] = f"{indent}{var_name} = {value}"
        next_line = len(lines)
        for next_node in tree.body[i+1:]:
            if hasattr(next_node, 'lineno'):
                next_line = next_node.lineno - 1
                break
        if next_line > start_line + 1:
            lines[start_line+1:next_line] = []
        changed = True

    return '\\n'.join(lines) if changed else code

if __name__ == "__main__":
    unittest.main()


test_main.py

A practical, hands-on course for aspiring data scientists ready to tackle real-world large data challenges. Learn to efficiently process, sample, and analyze massive datasets using Python and essential libraries. Each section features engaging video explanations and interactive challenges to build your expertise.

Learn foundational strategies for handling datasets too large to fit in memory, including chunking and streaming techniques.

Explore methods to balance and sample large datasets, including oversampling and undersampling.

Learn to use the polars library for fast, memory-efficient data processing.

Challenge: Chunked Data Aggregation

Lösung