Pandas & NumPy Quick Reference

import numpy as np

# Creation
a = np.array([1, 2, 3, 4])
zeros = np.zeros((2, 3))          # 2x3 array of 0.0
range_arr = np.arange(0, 10, 2)   # [0, 2, 4, 6, 8]
linspace = np.linspace(0, 1, 5)   # [0. , 0.25, 0.5 , 0.75, 1. ]

# Inspection
print(a.shape, a.dtype, a.ndim)   # (4,) int64 1

# Indexing & slicing
first_two = a[:2]                 # [1, 2] (a view)
mask = a[a > 2]                   # [3, 4] (a copy, boolean indexing)

# Aggregation
print(a.sum(), a.mean(), a.std(), a.max())

# Reshaping
grid = np.arange(6).reshape(2, 3)

import pandas as pd

df = pd.DataFrame({
    'customer': ['A', 'B', 'C', 'D'],
    'spend': [250.0, None, 180.5, 250.0],
    'active': [True, True, False, True]
})

# Selection
df.loc[df['active'], 'customer']          # customers where active is True
df.iloc[0:2, 0:2]                          # first 2 rows, first 2 columns
df[df['spend'] > 200]                      # boolean filter

# Cleaning
df['spend'] = df['spend'].fillna(df['spend'].mean())
df = df.drop_duplicates(subset=['customer'])
df.isna().sum()                            # count of missing values per column

import pandas as pd

orders = pd.DataFrame({'region': ['N','N','S','S'], 'amount': [100, 150, 90, 60]})
customers = pd.DataFrame({'region': ['N','S'], 'manager': ['Ana', 'Ravi']})

# Grouping
summary = orders.groupby('region').agg(total=('amount', 'sum'), avg=('amount', 'mean'))

# Merging (like a SQL JOIN)
merged = orders.merge(customers, on='region', how='left')

# Reshape wide -> long
wide = pd.DataFrame({'id': [1, 2], 'jan': [10, 20], 'feb': [15, 25]})
long = wide.melt(id_vars='id', var_name='month', value_name='value')

# Reshape long -> wide
pivoted = long.pivot(index='id', columns='month', values='value')