Python Tutorial (16): NumPy dan Pandas untuk Data Science

pip install numpy pandas

import numpy as np
 
# Buat array
arr = np.array([1, 2, 3, 4, 5])
zeros = np.zeros((3, 4))          # matrix 3x4 nol
ones = np.ones((2, 3))
range_arr = np.arange(0, 10, 2)   # [0, 2, 4, 6, 8]
linspace = np.linspace(0, 1, 5)   # 5 titik antara 0 dan 1
 
# Shape dan dtype
arr.shape      # (5,)
arr.dtype      # dtype('int64')
arr.reshape(5, 1)

import numpy as np
 
a = np.array([1, 2, 3, 4])
b = np.array([10, 20, 30, 40])
 
a + b          # [11, 22, 33, 44]
a * 2          # [2, 4, 6, 8]
a ** 2         # [1, 4, 9, 16]
np.sqrt(a)     # [1., 1.414, 1.732, 2.]
 
# Statistik
np.mean(a)     # 2.5
np.std(a)      # standard deviation
np.sum(a)      # 10
np.max(a)      # 4
np.argmax(a)   # index of max: 3

import numpy as np
 
matrix = np.array([
    [1, 2, 3],
    [4, 5, 6],
    [7, 8, 9],
])
 
matrix[0, 1]       # 2
matrix[:, 0]       # kolom pertama: [1, 4, 7]
matrix[1, :]       # baris kedua: [4, 5, 6]
matrix[matrix > 5] # [6, 7, 8, 9] (boolean indexing)

import numpy as np
 
matrix = np.array([[1, 2, 3], [4, 5, 6]])
matrix + 10      # tambah 10 ke semua elemen
matrix * np.array([1, 2, 3])  # multiply per kolom

import pandas as pd
 
# Dari dictionary
df = pd.DataFrame({
    "name": ["Alice", "Bob", "Charlie", "Diana"],
    "age": [30, 25, 35, 28],
    "city": ["Jakarta", "Bandung", "Jakarta", "Surabaya"],
    "salary": [15000000, 12000000, 18000000, 14000000],
})
 
print(df.head())
print(df.info())
print(df.describe())

import pandas as pd
 
# CSV
df = pd.read_csv("data.csv")
df.to_csv("output.csv", index=False)
 
# Excel
df = pd.read_excel("data.xlsx", sheet_name="Sheet1")
 
# JSON
df = pd.read_json("data.json")
df.to_json("output.json", orient="records")

import pandas as pd
 
# Kolom
df["name"]
df[["name", "salary"]]
 
# Baris by index
df.iloc[0]          # baris pertama
df.iloc[0:3]        # baris 0-2
df.loc[0, "name"]   # label-based
 
# Filter kondisional
df[df["age"] > 28]
df[(df["city"] == "Jakarta") & (df["salary"] > 14000000)]
df[df["name"].str.startswith("A")]

import pandas as pd
 
# Kolom baru
df["salary_m"] = df["salary"] / 1_000_000
df["is_senior"] = df["age"] >= 30
 
# Sort
df.sort_values("salary", ascending=False)
 
# Missing values
df.isnull().sum()
df.dropna()
df.fillna(0)
 
# Apply
df["name_upper"] = df["name"].apply(str.upper)

import pandas as pd
 
# Rata-rata gaji per kota
df.groupby("city")["salary"].mean()
 
# Multiple aggregations
df.groupby("city").agg({
    "salary": ["mean", "min", "max"],
    "age": "mean",
})
 
# Count per group
df.groupby("city").size()

import pandas as pd
 
orders = pd.DataFrame({
    "order_id": [1, 2, 3],
    "user_id": [101, 102, 101],
    "amount": [500, 300, 700],
})
 
users = pd.DataFrame({
    "user_id": [101, 102, 103],
    "name": ["Alice", "Bob", "Charlie"],
})
 
# SQL-like join
merged = pd.merge(orders, users, on="user_id", how="left")
# order_id | user_id | amount | name

import pandas as pd
 
sales = pd.DataFrame({
    "region": ["East", "West", "East", "West"],
    "product": ["A", "A", "B", "B"],
    "revenue": [100, 150, 200, 180],
})
 
pivot = sales.pivot_table(
    values="revenue",
    index="region",
    columns="product",
    aggfunc="sum",
)

import pandas as pd
import numpy as np
 
df = pd.DataFrame({"values": [1, 2, 3, 4, 5]})
 
# Akses sebagai NumPy array
arr = df["values"].to_numpy()
normalized = (arr - arr.mean()) / arr.std()
 
df["normalized"] = normalized

import pandas as pd
 
df = pd.read_csv("sales.csv", parse_dates=["date"])
 
# Filter Q1 2026
q1 = df[(df["date"] >= "2026-01-01") & (df["date"] < "2026-04-01")]
 
# Top 5 produk by revenue
top_products = (
    q1.groupby("product")["revenue"]
    .sum()
    .sort_values(ascending=False)
    .head(5)
)
 
print(top_products)
 
# Export summary
summary = q1.groupby("region").agg(
    total_revenue=("revenue", "sum"),
    avg_order=("revenue", "mean"),
    order_count=("order_id", "count"),
)
summary.to_csv("q1_summary.csv")