Summary  
This chapter explains how to import plain text files into pandas DataFrames using pd.read_csv with the sep parameter to define delimiters and header=None to handle files without column names.

General domain of usage  
Data analysis

`pandas`で**テキストファイル**を読み込むには、同じ関数`pd.read_csv()`を使用可能。テキストファイルを正しく読み込むためには、**区切り文字**や**デリミタ**を指定する追加パラメータ`sep`の利用が重要。

```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)
```

テキストファイルに**カラム名を含むヘッダー行**がない場合、`header`パラメータを`None`に設定。これにより、`pandas`は最初の行をカラム名として扱わない。

テキストファイルで一般的な改行を区切り文字として使用する場合、`sep='\r'`を設定。ここで、`'\r'`はキャリッジリターンを表し、新しい行を示す特殊文字。

注意

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を使用した実践的なデータ操作スキルの習得。SeriesおよびDataFrameの操作、データセットの読み込みと探索、データの選択とフィルタリング、集約処理、テーブルの再構成、複数のDataFrameの結合、分析のためのデータ準備。

TXTファイル

解答