Why Every Data Analyst Should Learn pandas in 2026

import pandas as pd

def clean_orders(df: pd.DataFrame) -> pd.DataFrame:
    df = df.copy()
    df.columns = [c.strip().lower().replace(" ", "_") for c in df.columns]
    df["city"] = df["city"].str.strip().str.title()
    df["order_date"] = pd.to_datetime(df["order_date"], dayfirst=True, errors="coerce")
    df["amount"] = pd.to_numeric(df["amount"].astype(str).str.replace(",", ""), errors="coerce")
    df = df.drop_duplicates(subset="order_id")
    return df

raw = pd.DataFrame({
    "Order ID": ["A1", "A2", "A2", "A3"],
    "City ": [" noida", "DELHI", "DELHI", "gurugram "],
    "Order Date": ["03/01/2026", "04/01/2026", "04/01/2026", "bad"],
    "Amount": ["1,200", "850", "850", "640"],
})
print(clean_orders(raw))

import pandas as pd

def quality_report(df: pd.DataFrame) -> pd.DataFrame:
    return pd.DataFrame({
        "dtype": df.dtypes.astype(str),
        "missing": df.isna().sum(),
        "missing_%": (df.isna().mean() * 100).round(1),
        "unique": df.nunique(),
    })

df = pd.DataFrame({"city": ["Noida", None, "Delhi"], "amount": [1200, 850, None]})
print(quality_report(df))

import pandas as pd

orders = pd.DataFrame({"order_id": [1, 2, 3], "customer_id": [10, 11, 99], "amount": [500, 300, 200]})
customers = pd.DataFrame({"customer_id": [10, 11], "segment": ["Retail", "Corporate"]})

merged = orders.merge(customers, on="customer_id", how="left",
                      validate="many_to_one", indicator=True)
unmatched = merged[merged["_merge"] == "left_only"]
print(merged.drop(columns="_merge"))
print(f"{len(unmatched)} order(s) without a matching customer:", unmatched["order_id"].tolist())

from pathlib import Path
import pandas as pd

# Create two small sample files so the example runs
Path("monthly").mkdir(exist_ok=True)
pd.DataFrame({"order_id": [1, 2], "amount": [100, 200]}).to_csv("monthly/2026-01.csv", index=False)
pd.DataFrame({"order_id": [3], "amount": [150]}).to_csv("monthly/2026-02.csv", index=False)

frames = []
for f in sorted(Path("monthly").glob("*.csv")):
    df = pd.read_csv(f)
    df["source_month"] = f.stem
    frames.append(df)
allmonths = pd.concat(frames, ignore_index=True)
print(allmonths)

import pandas as pd

df = pd.DataFrame({
    "date": pd.to_datetime(["2026-01-05", "2026-01-20", "2026-02-03", "2026-02-15", "2026-03-01"]),
    "region": ["North", "South", "North", "South", "North"],
    "amount": [1000, 700, 1200, 650, 1300],
})
df["month"] = df["date"].dt.to_period("M").astype(str)
pivot = df.pivot_table(index="region", columns="month", values="amount",
                       aggfunc="sum", fill_value=0, margins=True, margins_name="Total")
print(pivot)

import pandas as pd

df = pd.DataFrame({
    "date": pd.to_datetime(["2026-01-05", "2026-01-20", "2026-02-03", "2026-02-15", "2026-03-01"]),
    "amount": [1000, 700, 1200, 650, 1300],
})
monthly = df.set_index("date").resample("MS")["amount"].sum().to_frame()
monthly["mom_%"] = (monthly["amount"].pct_change() * 100).round(1)
monthly["running_total"] = monthly["amount"].cumsum()
print(monthly)

# pip install pandas openpyxl
import pandas as pd

def build_report(df: pd.DataFrame, path: str = "weekly_report.xlsx") -> None:
    df["week"] = df["date"].dt.to_period("W").astype(str)
    by_region = df.groupby("region", as_index=False)["amount"].sum()
    by_week = df.groupby("week", as_index=False)["amount"].sum()
    with pd.ExcelWriter(path) as xl:
        by_region.to_excel(xl, sheet_name="By region", index=False)
        by_week.to_excel(xl, sheet_name="By week", index=False)
        df.to_excel(xl, sheet_name="Data", index=False)
    print("saved", path)

sample = pd.DataFrame({
    "date": pd.to_datetime(["2026-03-02", "2026-03-04", "2026-03-10"]),
    "region": ["North", "South", "North"],
    "amount": [500, 300, 450],
})
build_report(sample)

Before sending an automated report:

[ ] Row count matches the source
[ ] No unexpected missing values
[ ] Totals match a manual spot check
[ ] Dates cover the right period
[ ] Sheet names and headers are clear
[ ] Script saved in Git with a short README

Week 1  Series, DataFrames, read_csv, read_excel
Week 2  Cleaning: types, strings, dates, nulls
Week 3  merge, concat, validation checks
Week 4  groupby, pivot_table, resample
Week 5  Export to Excel; automate a real weekly task
Week 6  Portfolio project with README