لدي مشكلة في اظهار توقعات بيانات(prediction) تويتر ودقتها(accuracy) بلغة البايثون(python)

السلام عليكم 

لدي مشروع عن تحليل بيانات تويتر بلغة البايثون

وعندما اعمل run للكود لاتظهرلي من البيانات في اخر فقرة (prediction) سوى سطرين فقط 

وكذلك الدقة تظهر 0.00 

علما انه عدد اسط بياناتي ٤١ 

وانا اريد منها ٢٠ سطر فقط

from pyspark.sql import SparkSession

from pyspark.ml.classification import LogisticRegression

from pyspark.ml.feature import Tokenizer,StopWordsRemover,CountVectorizer,IDF,StringIndexer

from pyspark.ml import Pipeline



spark = SparkSession.builder.getOrCreate()





df = spark.read.csv('test_data.tsv', sep='\t', encoding='utf-8', header=False).toDF('target', 'text')

print("Dataset schema:")

df.printSchema()

print("Training dataset:")

df.show(40)



# Print the numbeer of neg and pos tweets

import pandas as pd

print(df.toPandas().groupby(['target']).size())



# Split data into training and validation sets

(train_set, val_set) = df.randomSplit((0.9,0.1), seed=42)



# Arabic stop words

ar_stop_list = open("arabic_stopwords.txt", encoding="utf-8")

stop_words = ar_stop_list.read().split('\n')



# Text Preprocessing

tokenizer = Tokenizer(inputCol='text',outputCol='tokens')

stopwords_remover = StopWordsRemover(inputCol='tokens',outputCol='filtered_tokens').setStopWords(stop_words)

vectorizer = CountVectorizer(inputCol='filtered_tokens',outputCol='raw_features')

idf = IDF(inputCol='raw_features',outputCol='vectorized_features')

label_stringIdx = StringIndexer(inputCol='target',outputCol='label')

pipeline = Pipeline(stages=[tokenizer,stopwords_remover,vectorizer,idf,label_stringIdx])



pipeline_model = pipeline.fit(train_set)

train_df = pipeline_model.transform(train_set)

print("\nNew columns in training dataset:")

print(train_df.columns)

print("\nTransformed training dataset:")

train_df.show()



# For data classification into two classes (neg or pos),

# Fit logistic regression model to the transformed training dataframe

lr = LogisticRegression(maxIter=100, featuresCol='vectorized_features', labelCol='label')

lr_model = lr.fit(train_df)



# Evaluate the model using the validation dataframe

val_df = pipeline_model.transform(val_set)

predictions = lr_model.transform(val_df)



print("\nNew columns in validation dataset:")

print(predictions.columns)

print("\nTransformed validation dataset:")

# Show all generated columns

# predictions.show()

# Show only selected columns

predictions.select('target','label','prediction','text').show()

accuracy = predictions.filter(predictions.label == predictions.prediction).count() / float(val_set.count())

print("Accuracy Score: {0:.4f}".format(accuracy))

arabic_stopwords.txt