Lesson 7: Data Types, Conversion & Basic Cleaning

1. Understanding Data Types

Wrong types cause errors in ML (e.g. numbers stored as strings).

df.dtypes               # show types
df["age"] = df["age"].astype(int)   # convert to integer
df["date"] = pd.to_datetime(df["date"])  # parse dates

Common conversions:

• .astype(int/float/str)
• pd.to_numeric() — safe numeric conversion
• pd.to_datetime()
• pd.Categorical() — for categories

2. Basic Cleaning Tasks

• Remove duplicates: df.drop_duplicates()
• Rename columns: df.rename(columns={"old": "new"})
• Strip whitespace: df["name"] = df["name"].str.strip()
• Replace values: df["gender"] = df["gender"].replace({"M": "Male", "F": "Female"})
• Lowercase text: df["city"] = df["city"].str.lower()

These steps fix most common data quality issues.