1.将单词集与上一个产品和下一个产品进行比较
1.选择哪个邻居有较大的交集
1.选择没有进入交集的单词作为方差
这对您的示例是有效的，但是当产品描述中有多个重复的单词时，可能会给予奇怪的输出。
我还假设，如果描述与任何邻居都没有共同的词，它就没有组，因此没有方差。

def get_intersection(descr1, descr2):
    if pd.isna(descr1) or pd.isna(descr2):
        return set()
    return set(descr1.split()).intersection(set(descr2.split()))

def get_unique_words(descr, intersection):
    unique_words = " ".join(
        word for word in descr.split() if word not in intersection
    )
    if len(unique_words) > 0:
        return unique_words

def get_unique_description(row):
    if len(row["next_product_intersection"]) == 0 and len(row["prev_product_intersection"]) == 0:
        return row["Product Description"]
    
    if len(row["next_product_intersection"]) >= len(row["prev_product_intersection"]):
        return row["next_product_unique_words"]
    
    return row["prev_product_unique_words"]

df["next_product"] = df["Product Description"].shift(-1)
df["prev_product"] = df["Product Description"].shift(1)

df["next_product_intersection"] = df.apply(
    lambda row: get_intersection(row["Product Description"], row["next_product"]),
    axis=1
)
df["prev_product_intersection"] = df.apply(
    lambda row: get_intersection(row["Product Description"], row["prev_product"]),
    axis=1
)

df["next_product_unique_words"] = df.apply(
    lambda row: get_unique_words(row["Product Description"], row["next_product_intersection"]),
    axis=1
)
df["prev_product_unique_words"] = df.apply(
    lambda row: get_unique_words(row["Product Description"], row["prev_product_intersection"]),
    axis=1
)

df["Variance"] = df.apply(get_unique_description, axis=1)
df = df[["Product Description", "Variance"]]
print(df)

字符串
输出量：

Product Description      Variance
0                  Red HMS Carabiner           Red
1                 Blue HMS Carabiner          Blue
2               HMS Carabiner Orange        Orange
3               Liquid Chalk - 100ml          None
4  Liquid Chalk - 100ml (Case of 10)  (Case of 10)

型

这里有一个方法来解决你的问题：

import difflib
import pandas as pd

def get_products_variants(df: pd.DataFrame) -> pd.DataFrame:
    """
    Get variants for every product description.

    Parameters
    ----------
    df : pd.DataFrame
        A `pandas.DataFrame` with a column named "Product Description",
        that contains every existing product description.

    Returns
    -------
    pd.DataFrame
        A `pandas.DataFrame` with the columns:
            - "Product Description": The common name between variants of same product.
            - "Variance": The product variant.

    Examples
    --------
    >>> test_df = pd.DataFrame(
    ...     {
    ...         "Product Description": [
    ...             "Red HMS Carabiner", "Blue HMS Carabiner", "HMS Carabiner Orange",
    ...             "Liquid Chalk - 100ml", "Liquid Chalk - 100ml (Case of 10)"
    ...         ]
    ...     }
    ... )
    >>> get_products_variants(test_df)
         Product Description      Variance
    0          HMS Carabiner           Red
    1          HMS Carabiner          Blue
    2          HMS Carabiner        Orange
    9   Liquid Chalk - 100ml              
    10  Liquid Chalk - 100ml  (Case of 10)
    """
    new_data = []

    for description in df["Product Description"].values:
        # Split product descriptions into different words
        words = description.split(" ")
        # Find product descriptions that are closely related to the current
        # product description.
        matches = difflib.get_close_matches(description, df["Product Description"].values)

        # Iterate the descriptions that are similar to current product description
        # to find the words that exist in all product descriptions
        for descr in matches:
            descr_words = descr.split(" ")
            _words = []
            for word in descr_words:
                if word in words:
                    _words.append(word)
            words = _words

        # This new description is comprised of words that exist in all product descriptions
        # that have similar names.
        new_description = " ".join(words)

        # Find the words that are unique to each product description.
        # These words will be the variants
        for descr in matches:
            variance = descr.replace(new_description, "").strip()
            new_data.append([new_description, variance])

    # Create new dataframe with results
    return pd.DataFrame(new_data, columns=["Product Description", "Variance"]).drop_duplicates()

df = pd.DataFrame(
    {
        "Product Description": [
            "Red HMS Carabiner", "Blue HMS Carabiner", "HMS Carabiner Orange",
            "Liquid Chalk - 100ml", "Liquid Chalk - 100ml (Case of 10)"
        ]
    }
)
new_df = get_products_variants(df)
new_df
# Returns:
#
#      Product Description      Variance
# 0          HMS Carabiner           Red
# 1          HMS Carabiner          Blue
# 2          HMS Carabiner        Orange
# 9   Liquid Chalk - 100ml              
# 10  Liquid Chalk - 100ml  (Case of 10)

字符串

输出：

| | 方差| Variance |
| --|--|--|
| 0 |铁钩号驱逐舰|红色|
| 1 |铁钩号驱逐舰|蓝色|
| 2 |铁钩号驱逐舰|橙子|
| 9 |液体粉笔-100毫升||
| 10 |液体粉笔-100毫升|（10例）|

注意事项

要查找相似的产品描述，我们使用difflib模块（Python默认自带的模块）中的get_close_matches函数。根据产品描述的不同，get_close_matches可能无法找到某个产品的所有相似产品描述。换句话说，上述解决方案并不保证适用于所有情况。