Pandas2 Solutions

article-views-i.py

@@ -0,0 +1,62 @@
+"""
+
+Table: Views
+
++---------------+---------+
+| Column Name   | Type    |
++---------------+---------+
+| article_id    | int     |
+| author_id     | int     |
+| viewer_id     | int     |
+| view_date     | date    |
++---------------+---------+
+There is no primary key (column with unique values) for this table, the table may have duplicate rows.
+Each row of this table indicates that some viewer viewed an article (written by some author) on some date. 
+Note that equal author_id and viewer_id indicate the same person.
+
+
+Write a solution to find all the authors that viewed at least one of their own articles.
+
+Return the result table sorted by id in ascending order.
+
+The result format is in the following example.
+
+
+Example 1:
+
+Input: 
+Views table:
++------------+-----------+-----------+------------+
+| article_id | author_id | viewer_id | view_date  |
++------------+-----------+-----------+------------+
+| 1          | 3         | 5         | 2019-08-01 |
+| 1          | 3         | 6         | 2019-08-02 |
+| 2          | 7         | 7         | 2019-08-01 |
+| 2          | 7         | 6         | 2019-08-02 |
+| 4          | 7         | 1         | 2019-07-22 |
+| 3          | 4         | 4         | 2019-07-21 |
+| 3          | 4         | 4         | 2019-07-21 |
++------------+-----------+-----------+------------+
+Output: 
++------+
+| id   |
++------+
+| 4    |
+| 7    |
++------+
+
+"""
+
+# The function filters the DataFrame to include only rows where the author_id matches the viewer_id, 
+# meaning the author viewed their own article. It then removes duplicate author_id entries to ensure 
+# each author appears only once and sorts the results before returning the final DataFrame.
+
+import pandas as pd
+
+def article_views(views: pd.DataFrame) -> pd.DataFrame:
+
+    df = views[views['author_id'] == views['viewer_id']]
+    df.drop_duplicates(subset=['author_id'], inplace=True)
+    df.sort_values(by=['author_id'], inplace=True)
+
+    return df[['author_id']].rename(columns={'author_id': 'id'})

invalid-tweets.py

@@ -0,0 +1,56 @@
+"""
+
+Table: Tweets
+
++----------------+---------+
+| Column Name    | Type    |
++----------------+---------+
+| tweet_id       | int     |
+| content        | varchar |
++----------------+---------+
+tweet_id is the primary key (column with unique values) for this table.
+content consists of characters on an American Keyboard, and no other special characters.
+This table contains all the tweets in a social media app.
+
+
+Write a solution to find the IDs of the invalid tweets. The tweet is invalid if the number of characters used in the content of the tweet is strictly greater than 15.
+
+Return the result table in any order.
+
+The result format is in the following example.
+
+
+Example 1:
+
+Input: 
+Tweets table:
++----------+-----------------------------------+
+| tweet_id | content                           |
++----------+-----------------------------------+
+| 1        | Let us Code                       |
+| 2        | More than fifteen chars are here! |
++----------+-----------------------------------+
+
+Output: 
++----------+
+| tweet_id |
++----------+
+| 2        |
++----------+
+
+Explanation: 
+Tweet 1 has length = 11. It is a valid tweet.
+Tweet 2 has length = 33. It is an invalid tweet.
+
+"""
+
+# The function filters out tweets where the 'content' length is 15 characters or less.  
+# It creates a boolean mask to identify valid tweets and selects only those that meet the condition.  
+# Finally, it returns a DataFrame containing only the 'tweet_id' column of the valid tweets.  
+
+import pandas as pd
+
+def invalid_tweets(tweets: pd.DataFrame) -> pd.DataFrame:
+   isValid = tweets['content'].str.len() > 15
+   df = tweets[isValid]
+   return df[['tweet_id']]