Common Data Cleaning Techniques for Data Analysts

Remove Duplicates:

Purpose: Eliminate repeated rows to maintain unique data.

Example: SELECT DISTINCT column_name FROM table;


Handle Missing Values:

Purpose: Fill, remove, or impute missing data.

Example:

Remove: df.dropna() (in Python/Pandas)

Fill: df.fillna(0)


Standardize Data:

Purpose: Convert data to a consistent format (e.g., dates, numbers).

Example: Convert text to lowercase: df['column'] = df['column'].str.lower()


Remove Outliers:

Purpose: Identify and remove extreme values.

Example: df = df[df['column'] < threshold]


Correct Data Types:

Purpose: Ensure columns have the correct data type (e.g., dates as datetime, numeric values as integers).

Example: df['date'] = pd.to_datetime(df['date'])


Normalize Data:

Purpose: Scale numerical data to a standard range (0 to 1).

Example: from sklearn.preprocessing import MinMaxScaler; df['scaled'] = MinMaxScaler().fit_transform(df[['column']])


Data Transformation:

Purpose: Transform or aggregate data for better analysis (e.g., log transformations, aggregating columns).

Example: Apply log transformation: df['log_column'] = np.log(df['column'] + 1)


Handle Categorical Data:

Purpose: Convert categorical data into numerical data using encoding techniques.

Example: df['encoded_column'] = pd.get_dummies(df['category_column'])


Impute Missing Values:

Purpose: Fill missing values with a meaningful value (e.g., mean, median, or a specific value).

Example: df['column'] = df['column'].fillna(df['column'].mean())

I have curated best 80+ top-notch Data Analytics Resources 👇👇
https://whatsapp.com/channel/0029VaGgzAk72WTmQFERKh02

Like this post for more content like this 👍♥️

Share with credits: https://t.me/sqlspecialist

Hope it helps :)