Solutions.Rmd

```{r, include = FALSE}
# enable python code previews; must use python 3
library(reticulate)
use_python("/usr/bin/python3")

ottrpal::set_knitr_image_path()
```

# Solutions {-}

## Refactoring Hands-On Exercise Solutions {-}

Create an AI prompt that fixes any formatting issues with the code that would cause it not to run.
    
:::{.query}
Can you help me fix any formatting issues in the following python code?
:::

:::{.ai_response}
```{python eval = FALSE, python.reticulate = FALSE}
import tweepy
import pandas

# Enter your API keys and access tokens here
consumer_key = 'your_consumer_key'
consumer_secret = 'your_consumer_secret'
access_token = 'your_access_token'
access_token_secret = 'your_access_token_secret'

# Authenticate with Twitter API
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)

# Search for tweets containing the search term
tweets = tweepy.Cursor(tweepy.API(auth).search_tweets, q="Mr. Trash Wheel", tweet_mode='extended').items(100)

# Create empty list to store tweet data
date_data = []
location_data = []
text_data = []

def get_tweet_length(tweet):
    # Return the length of the tweet text
    return len(tweet.full_text)

# Loop through each tweet and extract desired data
for tweet in tweets:
    date_info = {
        'date': tweet.created_at
    }
    date_data.append(date_info)

# Search for tweets containing the search term
tweets = tweepy.Cursor(tweepy.API(auth).search_tweets, q="Mr. Trash Wheel", tweet_mode='extended').items(100)

# Loop through each tweet and extract desired data
for tweet in tweets:
    location_info = {
        'location': tweet.user.location
    }
    location_data.append(location_info)

# Search for tweets containing the search term
tweets = tweepy.Cursor(tweepy.API(auth).search_tweets, q='Mr. Trash Wheel', tweet_mode='extended').items(100)

# Loop through each tweet and extract desired data
for tweet in tweets:
    text_info = {
        'text': tweet.full_text
    }
    text_data.append(text_info)

# Combine lists into a dictionary
data = {'date': date_data, 'location': location_data, 'text': text_data}

# Store results in pandas dataframe
df = pandas.DataFrame(data)

# Print dataframe
print(df)
```
:::

Devise an AI prompt that removes any dead code from your sample above. What gets removed?

:::{.query}
Can you remove any unused functions from this python code?
:::

:::{.ai_response}
Yes, the `get_tweet_length()` function is not being used in this code. It can be removed.

```{python eval = FALSE, python.reticulate = FALSE}
import tweepy
import pandas

# Enter your API keys and access tokens here
consumer_key = 'your_consumer_key'
consumer_secret = 'your_consumer_secret'
access_token = 'your_access_token'
access_token_secret = 'your_access_token_secret'

# Authenticate with Twitter API
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)

# Search for tweets containing the search term
tweets = tweepy.Cursor(tweepy.API(auth).search_tweets, q="Mr. Trash Wheel", tweet_mode='extended').items(100)

# Create empty list to store tweet data
date_data = []
location_data = []
text_data = []

# Loop through each tweet and extract desired data
for tweet in tweets:
    date_info = {
        'date': tweet.created_at
    }
    date_data.append(date_info)

# Search for tweets containing the search term
tweets = tweepy.Cursor(tweepy.API(auth).search_tweets, q="Mr. Trash Wheel", tweet_mode='extended').items(100)

# Loop through each tweet and extract desired data
for tweet in tweets:
    location_info = {
        'location': tweet.user.location
    }
    location_data.append(location_info)

# Search for tweets containing the search term
tweets = tweepy.Cursor(tweepy.API(auth).search_tweets, q='Mr. Trash Wheel', tweet_mode='extended').items(100)

# Loop through each tweet and extract desired data
for tweet in tweets:
    text_info = {
        'text': tweet.full_text
    }
    text_data.append(text_info)

# Combine lists into a dictionary
data = {'date': date_data, 'location': location_data, 'text': text_data}

# Store results in pandas dataframe
df = pandas.DataFrame(data)

# Print dataframe
print(df)
```
::: 


Create a prompt that makes the code less repetitive, adhering to the DRY principle. What aspect of the code was repetitive?

:::{.query}
Can you help make this code more DRY?
:::
    
:::{.ai_response}
Yes, you can make this code more DRY by removing the code repetition. You can combine the three for loops into a single loop and extract all the desired data in one go. Here's an updated version of the code:

```{python eval = FALSE, python.reticulate = FALSE}
import tweepy
import pandas
    
# Enter your API keys and access tokens here
consumer_key = 'your_consumer_key'
consumer_secret = 'your_consumer_secret'
access_token = 'your_access_token'
access_token_secret = 'your_access_token_secret'
    
# Authenticate with Twitter API
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
    
# Search for tweets containing the search term
tweets = tweepy.Cursor(tweepy.API(auth).search_tweets, q="Mr. Trash Wheel", tweet_mode='extended').items(100)
    
# Create empty list to store tweet data
data = []
    
# Loop through each tweet and extract desired data
for tweet in tweets:
    tweet_data = {
        'date': tweet.created_at,
        'location': tweet.user.location,
        'text': tweet.full_text
    }
    data.append(tweet_data)
    
# Store results in pandas dataframe
df = pandas.DataFrame(data)
    
# Print dataframe
print(df)

```

This code extracts the date, location, and text data in one loop, and appends them to a single `tweet_data` dictionary. The data list is populated with these dictionaries, and then used to create the pandas dataframe.
::: 

Construct a prompt that makes the code more concise. What are some trade-offs that appear in this code between readability and brevity?

:::{.query}
Can you make the following python code more concise?
:::

:::{.ai_response}
```{python eval = FALSE, python.reticulate = FALSE}
import tweepy
import pandas as pd

# Enter your API keys and access tokens here
consumer_key = 'your_consumer_key'
consumer_secret = 'your_consumer_secret'
access_token = 'your_access_token'
access_token_secret = 'your_access_token_secret'

# Authenticate with Twitter API
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)

# Search for tweets containing the search term
tweets = tweepy.Cursor(api.search_tweets, q="Mr. Trash Wheel", tweet_mode='extended').items(100)

# Extract desired data from each tweet and store in a list
data = [{'date': tweet.created_at, 'location': tweet.user.location, 'text': tweet.full_text} for tweet in tweets]

# Store results in pandas dataframe
df = pd.DataFrame(data)

# Print dataframe
print(df)
```

This version removes the duplicate search code by combining the three search loops into one, and simplifies the loop to a list comprehension.

The list comprehension format might be less readable or intuitive to some programmers.
:::