Why Every Data Analyst Should Learn Python in 2026

import glob
import pandas as pd

files = glob.glob("sales/*.xlsx")          # all monthly files
frames = [pd.read_excel(f) for f in files]
sales = pd.concat(frames, ignore_index=True)
sales.to_csv("all_sales.csv", index=False)
print(len(files), "files combined into", len(sales), "rows")

print(sales.shape)          # rows, columns
print(sales.dtypes)         # column types
print(sales.isna().sum())   # missing values per column
print(sales.head())         # first five rows

import pandas as pd

df = pd.read_csv("all_sales.csv")
df["city"] = df["city"].str.strip().str.title()
df["order_date"] = pd.to_datetime(df["order_date"], errors="coerce")
df = df.dropna(subset=["order_date"])
df["amount"] = df["amount"].fillna(0)
df = df.drop_duplicates(subset=["order_id"])

df["month"] = df["order_date"].dt.to_period("M").astype(str)
summary = (
    df.groupby(["month", "city"], as_index=False)["amount"]
      .sum()
      .sort_values(["month", "amount"], ascending=[True, False])
)
print(summary.head(10))

with pd.ExcelWriter("weekly_report.xlsx") as writer:
    summary.to_excel(writer, sheet_name="By city", index=False)
    top = df.nlargest(10, "amount")
    top.to_excel(writer, sheet_name="Top orders", index=False)
print("weekly_report.xlsx created")

import matplotlib.pyplot as plt

monthly = df.groupby("month")["amount"].sum()
monthly.plot(kind="bar", title="Revenue by month")
plt.ylabel("Revenue")
plt.tight_layout()
plt.savefig("revenue_by_month.png", dpi=150)

import pandas as pd

df = pd.read_csv("input.csv")
print("Rows, columns:", df.shape)
print("\nMissing values:\n", df.isna().sum())
print("\nDuplicates:", df.duplicated().sum())
print("\nNumeric summary:\n", df.describe())
for col in df.select_dtypes("object"):
    print(f"\n{col}: {df[col].nunique()} unique values")

import pandas as pd

old = pd.read_csv("last_week.csv")
new = pd.read_csv("this_week.csv")
merged = old.merge(new, on="id", how="outer",
                   suffixes=("_old", "_new"), indicator=True)
print(merged["_merge"].value_counts())
changed = merged[(merged["_merge"] == "both") &
                 (merged["amount_old"] != merged["amount_new"])]
print(len(changed), "rows changed")

Before running any analysis script:
[ ] Input file is the latest version
[ ] Column names match what the script expects
[ ] Row count looks reasonable
[ ] Output folder exists
After running:
[ ] Totals match a quick manual check
[ ] Charts have titles and labels
[ ] Report saved with today's date in the name