Summary  
This chapter explains how to read text files into a pandas DataFrame by specifying a custom separator (`sep`) and handling files without header rows (`header=None`).

General domain of usage  
Data analysis

To read **text files** in `pandas`, you can use the same function, `pd.read_csv()`. However, to ensure the text file is read correctly, it's essential to use an additional parameter called `sep`, which stands for **separator** or **delimiter** in the text.

```python
# Importing pandas library
import pandas as pd

# Reading a text file into a DataFrame
text_data = pd.read_csv('file.txt', sep='\r', header=None)
```

If your text file doesn't have a **header row** containing column names, set the `header` parameter to `None`. Doing so informs `pandas` not to treat the first row as column names.

> Note
> 
> To use a new line as the separator in a file, which is common in text files, set `sep='\r'`. Here, `'\r'` stands for a carriage return, which is a special character used to indicate a new line.

import unittest
import importlib
import pandas as pd


# Helper function to dynamically generate test names and assertions
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 get_first_differing_row(expected_df, actual_df):
    expected_list = expected_df.astype(str).apply(tuple, axis=1)
    actual_list = actual_df.astype(str).apply(tuple, axis=1)

    for i, (row1, row2) in enumerate(zip(expected_list, actual_list)):
        if row1 != row2:
            return i, expected_df.iloc[i].values, actual_df.iloc[i].values

    if len(expected_df) > len(actual_df):
        return len(actual_df), expected_df.iloc[len(actual_df)].values, None
    else:
        return len(expected_df), None, actual_df.iloc[len(expected_df)].values


class TestUserCode(unittest.TestCase):

    def test_text_data_is_declared(self):
        import user_code
        _dynamic_test(
            self,
            hasattr(user_code, 'text_data'),
            "The `text_data` variable is declared.",
            "Expected `text_data` to be declared."
        )

    def test_text_data_is_dataframe(self):
        import user_code

        try:
            condition = isinstance(user_code.text_data, pd.DataFrame)
            failure_message = f"Expected `text_data` to be a `DataFrame`, but got `{type(user_code.text_data).__name__}`."
        except AttributeError:
            condition = False
            failure_message = "The `text_data` variable is not declared."

        _dynamic_test(
            self,
            condition,
            "The variable `text_data` is a `DataFrame`.",
            failure_message
        )

    def test_text_data_is_correct(self):
        import user_code
        row_1 = 'pandas is a software library written for the Python programming language for data manipulation and analysis. In particular, it offers data structures and operations for manipulating numerical tables and time series. It is free software released under the three-clause BSD license.[2] The name is derived from the term "panel data", an econometrics term for data sets that include observations over multiple time periods for the same individuals.[3] Its name is a play on the phrase "Python data analysis" itself.[4] Wes McKinney started building what would become pandas at AQR Capital while he was a researcher there from 2007 to 2010.[5]'
        row_2 = "taken from the site:"
        row_3 = "https://en.wikipedia.org/wiki/Pandas_(software)"
        expected_df = pd.DataFrame([row_1, row_2, row_3])

        variable = 'text_data'
        actual_df = getattr(user_code, variable, None)
        condition = False
        if actual_df is None:
            failure_message = f"The `{variable}` variable is not declared."
        elif not isinstance(actual_df, pd.DataFrame):
            failure_message = f"`{variable}` is not a `DataFrame`."
        elif actual_df.empty:
            failure_message = f"`{variable}` is empty."
        elif actual_df.equals(expected_df):
            condition = True
            failure_message = None
        else:
            idx, expected_row, actual_row = get_first_differing_row(expected_df, actual_df)
            failure_message = f"Expected `{variable}` to contain `{expected_row}` at row {idx}, but got `{actual_row}`."

        _dynamic_test(
            self,
            condition,
            f"`{variable}` contains the correct data.",
            failure_message
        )

    def test_first_row_is_declared(self):
        import user_code
        _dynamic_test(
            self,
            hasattr(user_code, 'first_row'),
            "The `first_row` variable is declared.",
            "Expected `first_row` to be declared."
        )

    def test_first_row_is_series(self):
        import user_code

        try:
            condition = isinstance(user_code.first_row, pd.Series)
            failure_message = f"Expected `first_row` to be a `Series`, but got `{type(user_code.first_row).__name__}`."
        except AttributeError:
            condition = False
            failure_message = "The `first_row` variable is not declared."

        _dynamic_test(
            self,
            condition,
            "The variable `first_row` is a `Series`.",
            failure_message
        )

    def test_first_row_is_correct(self):
        import user_code
        row_1 = 'pandas is a software library written for the Python programming language for data manipulation and analysis. In particular, it offers data structures and operations for manipulating numerical tables and time series. It is free software released under the three-clause BSD license.[2] The name is derived from the term "panel data", an econometrics term for data sets that include observations over multiple time periods for the same individuals.[3] Its name is a play on the phrase "Python data analysis" itself.[4] Wes McKinney started building what would become pandas at AQR Capital while he was a researcher there from 2007 to 2010.[5]'
        row_2 = "taken from the site:"
        row_3 = "https://en.wikipedia.org/wiki/Pandas_(software)"
        expected_df = pd.DataFrame([row_1, row_2, row_3])
        expected_value = expected_df.iloc[0]

        variable = 'first_row'
        actual_value = getattr(user_code, variable, None)
        if actual_value is None:
            condition = False
            failure_message = f"The `{variable}` variable is not declared."
        elif isinstance(actual_value, pd.Series):
            condition = actual_value.equals(expected_value)
            if actual_value.empty:
                failure_message = f"`{variable}` is empty."
            else:
                failure_message = f"Expected `{variable}` to contain `{expected_value.values}`, but got `{actual_value.values}`."
        else:
            condition = False
            failure_message = f"`{variable}` is not a `Series`."

        _dynamic_test(
            self,
            condition,
            f"`first_row` contains the correct values.",
            failure_message
        )


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

test_main.py

Pandas is an extremely user-friendly library for data analysis. It's also designed to handle large datasets, using data structures like DataFrame and Series. This makes it an invaluable tool for Data Science. In this guide, you'll get acquainted with a range of statistical functions, including how to find correlations, modes, medians, and maximum and minimum values within a dataset. You'll also learn how to handle missing values and manipulate specific values, as well as how to remove them.

In this section, we'll explore the fundamentals of Series and DataFrame structures. You'll also learn about the distinctions between these two types of structures.

Data can be sourced in various formats, such as CSV, JSON, SQL, HTML, and more. With Pandas, you're not limited to a single format — you can work with data across a multitude of file types. In this chapter, we'll specifically focus on the CSV and TXT formats.

Here, you'll learn how to process raw data by removing extraneous information and managing null values in a dataset.

TXT Files

Solution

Awesome!

TXT Files

Solution