L15: Applied ChatGPT for Text Analysis

# Import the necessary OpenAI client library
# Make sure you have installed the OpenAI Python package: `pip install openai`

def get_completion(prompt):
    response = client.chat.completions.create(
        model="gpt-3.5-turbo-0125",
        messages=[{"role": "user", "content": prompt}],
        temperature=0,  # this is the degree of randomness of the model's output
    )
    return response.choices[0].message.content

# Assuming longest_review is defined and contains text
prompt_template = """
Task: Summarize the e-commerce product review below.

Instructions:

1. Create a shortened version of the review in 50 words or fewer.
2. Use first person and immitate the reviewer's tone directly.
3. Do not add any opinions, explanations, conversational tone, or new information.
4. Simply condense the main points as written by the reviewer.

Review: 
```{review_text_here}```
"""

def summarize_review(prompt, review_text):
    # Replace placeholder in the prompt with the review text
    formatted_prompt = prompt.replace("{review_text_here}", review_text)
    
    # Generate the summary using get_completion
    summary = get_completion(formatted_prompt)
    return summary

short_longest_review = summarize_review(prompt=prompt_template, review_text=longest_review)
print(short_longest_review)

count_more_than_200 = (docs["word_count"] > 200).sum()
print(count_more_than_200)

# Apply the function only where word_count > 200
def process_row(row):
    if row["word_count"] > 200:
        summary = summarize_review(prompt=prompt_template, review_text=row["review_text"])
        print(f"Processed row {row.name}: Summary created")
        print(summary)
        return summary
    else:
        print(f"Processed row {row.name}: No summary needed (word_count <= 200)")
        return None
      
# Apply the function to process each row
docs["summary"] = docs.apply(process_row, axis=1)

# Assuming longest_review is defined and contains text
prompt_template2 = """
Task: Summarize the e-commerce product review below, delimited by triple backticks,\
to provide feedback to the engineering department responsible for the product's design.

Instructions:

1. Create a concise summary in at most 30 words.
2. Focus specifically on aspects relevant to the product's design or engineering.
3. If the review does not mention design or engineering, respond with exactly the\
word "None" (without quotes or additional text).

Review: 
```{review_text_here}```
"""

def process_row(row):
    formatted_prompt = prompt_template2.replace("{review_text_here}", row["review_text"])
    summary = get_completion(formatted_prompt).strip()
    return summary

# Apply the function to process each row
docs_10["targeted_summary"] = docs_10.apply(process_row, axis=1)
docs_10_filtered = docs_10[docs_10["targeted_summary"] != "None"]
docs_10_filtered

prompt = f"""
What is the sentiment of the following product review, which is delimited\
with triple backticks?

Review: 
```{review}```
"""

response = get_completion(prompt)
print(response)

text = """
Needed a nice lamp for my bedroom, and this one had \
additional storage and not too high of a price point. \
Got it fast.  The string to our lamp broke during the \
transit and the company happily sent over a new one. \
Came within a few days as well. It was easy to put \
together.  I had a missing part, so I contacted their \
support and they very quickly got me the missing piece! \
Lumina seems to me to be a great company that cares \
about their customers and products!!
"""

prompt = f"""
Identify a list of emotions that the writer of the \
following review is expressing. Include no more than \
five items in the list. Format your answer as a list of \
lower-case words separated by commas.

Review text: '''{text}'''
"""

response = get_completion(prompt)
print(response)

text = """
Needed a nice lamp for my bedroom, and this one had \
additional storage and not too high of a price point. \
Got it fast.  The string to our lamp broke during the \
transit and the company happily sent over a new one. \
Came within a few days as well. It was easy to put \
together.  I had a missing part, so I contacted their \
support and they very quickly got me the missing piece! \
Lumina seems to me to be a great company that cares \
about their customers and products!!
"""

prompt = f"""
Identify the following items from the review text: 
- Item purchased by reviewer
- Company that made the item

The review is delimited with triple backticks. \
Format your response as a JSON object with \
"Item" and "Brand" as the keys. 
If the information isn't present, use "unknown" \
as the value.
Make your response as short as possible.
  
Review text: '''{text}'''
"""

response = get_completion(prompt)
print(response)

prompt = f"""
Identify the following items from the review text: 
- Sentiment (positive or negative)
- Is the reviewer expressing anger? (true or false)
- Item purchased by reviewer
- Company that made the item

The review is delimited with triple backticks. \
Format your response as a JSON object with \
"Sentiment", "Anger", "Item" and "Brand" as the keys.
If the information isn't present, use "unknown" \
as the value.
Make your response as short as possible.
Format the Anger value as a boolean.

Review text: '''{text}'''
"""

response = get_completion(prompt)
print(response)

prompt = f"""
Determine five topics that are being discussed in the \
following text, which is delimited by triple backticks.

Make each item one or two words long. 

Format your response as a list of uncounted items separated by commas.

Text sample: 
'''{speech}'''
"""

response = get_completion(prompt)
print(response)

response.split(sep=',')

topic_list = ["brexit", "UK-EU relations", "rails", "transport", "aliens"]

prompt = f"""
Determine whether each item in the following list of \
topics is a topic in the text below, which
is delimited with triple backticks.

Format your response as a JSON object with \
the topics as the keys.

Give your answer as follows:
item from the list: 0 or 1

List of topics: {", ".join(topic_list)}

Text sample: '''{speech}'''
"""

response = get_completion(prompt)
print(response)

text_to_translate = "I love what I can do with ChatGPT OpenAI."

prompt = f"""
Translate the following English text to Italian which
is delimited with triple backticks.:\

Text sample: '''{text_to_translate}'''
"""

response = get_completion(prompt)
print(response)

text_to_fix = """
This is a mock short paragraf to see how ChatGPT performs when it comes to\ 
grammer and spelling. These is a wrong sentence. Speling is of.
"""

prompt = f"""
Proofread and correct the following text, which
is delimited with triple backticks.

Rewrite the corrected version a simple string.

If you don't find and errors, leave as such.

```{text_to_fix}```
"""
response = get_completion(prompt)
print(response)