将每个二元语法从列表格式移动到Pandas或Pyspark数据帧中的新行

bigrams_list = [('hello', 'world'), ('world', 'is'), ('is', 'great')]

import pandas as pd

# 创建DataFrame
df = pd.DataFrame(bigrams_list, columns=['word1', 'word2'])

print(df)

  word1   word2
0 hello   world
1 world     is
2   is   great

bigrams_list = [('hello', 'world'), ('world', 'is'), ('is', 'great')]

from pyspark.sql import SparkSession

# 创建SparkSession
spark = SparkSession.builder.appName("example").getOrCreate()

# 创建DataFrame
df = spark.createDataFrame(bigrams_list, ["word1", "word2"])

df.show()

+-----+-----+
|word1|word2|
+-----+-----+
|hello|world|
|world|   is|
|  is |great|
+-----+-----+

# 示例：确保列表中的元素都是字符串
bigrams_list = [('hello', 'world'), ('world', 'is'), ('is', 'great')]

# 示例：使用PySpark处理大规模数据
spark = SparkSession.builder.appName("example").config("spark.executor.memory", "8g").getOrCreate()