Learning-Hub/pandas-notes.html at main · Developer-Sahil/Learning-Hub · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Pandas Guide - Learning Hub</title>
    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/themes/prism-tomorrow.min.css">
    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;800&family=Fira+Code&display=swap" rel="stylesheet">
    <link rel="stylesheet" href="css/common.css">
    <link rel="stylesheet" href="css/notes.css">
</head>
<body>
    <div class="particles" id="particles"></div>

    <nav class="navbar">
        <div class="nav-container">
            <a href="index.html" class="nav-brand">📚 Learning Hub</a>
            <div class="nav-links">
                <a href="index.html">Home</a>
                <a href="python-notes.html">Python</a>
                <a href="numpy-notes.html">NumPy</a>
                <!-- <a href="pandas-notes.html">Pandas</a> -->
                <a href="sql-notes.html">SQL</a>
                <a href="statistics-notes.html">Statistics</a>
                <a href="about.html">About</a>
            </div>
        </div>
    </nav>

    <div class="container">
        <aside class="sidebar">
            <h3>📖 Contents</h3>
            <ul>
                <li><a href="#intro" class="active">Introduction</a></li>
                <li><a href="#install">Installation</a></li>
                <li><a href="#series">Series</a></li>
                <li><a href="#dataframes">DataFrames</a></li>
                <li><a href="#reading">Reading Data</a></li>
                <li><a href="#viewing">Viewing Data</a></li>
                <li><a href="#selection">Selection & Indexing</a></li>
                <li><a href="#filtering">Filtering</a></li>
                <li><a href="#operations">Operations</a></li>
                <li><a href="#grouping">GroupBy</a></li>
                <li><a href="#merging">Merging & Joining</a></li>
                <li><a href="#missing">Missing Data</a></li>
                <li><a href="#apply">Apply Functions</a></li>
                <li><a href="#time-series">Time Series</a></li>
                <li><a href="#export">Exporting Data</a></li>
            </ul>
        </aside>

        <main class="content">
            <div class="hero">
                <h1>🐼 Pandas Handbook</h1>
                <p>Master data manipulation and analysis with DataFrames, Series, and powerful data operations</p>
            </div>

            <section id="intro" class="card">
                <h2>1. Introduction to Pandas</h2>
                <p>Pandas is the most popular Python library for data manipulation and analysis. It provides powerful, flexible data structures designed for working with structured (tabular, multidimensional, potentially heterogeneous) and time series data.</p>

                <div class="highlight-box">
                    <p><strong>Why Pandas?</strong> Fast and efficient DataFrame objects, tools for reading/writing data, data alignment and missing data handling, reshaping and pivoting</p>
                </div>

                <p>Pandas is built on top of NumPy and is a key library for:</p>
                <ul>
                    <li><strong>Data Cleaning</strong> - Handle missing data, duplicates, and inconsistencies</li>
                    <li><strong>Data Transformation</strong> - Reshape, pivot, merge, and aggregate</li>
                    <li><strong>Data Analysis</strong> - Statistical analysis and exploration</li>
                    <li><strong>Time Series</strong> - Work with dates, times, and time-indexed data</li>
                </ul>
            </section>

            <section id="install" class="card">
                <h2>2. Installation and Import</h2>

                <div class="code-container">
                    <div class="code-header">
                        <span>Bash</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-bash"># Install with pip
$ pip install pandas

# Or with Anaconda
$ conda install pandas</code></pre>
                </div>

                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python">import pandas as pd
import numpy as np

# Check version
print(pd.__version__)  # 1.3.0 or newer</code></pre>
                </div>
            </section>

            <section id="series" class="card">
                <h2>3. Series</h2>
                <p>A Series is a one-dimensional labeled array capable of holding any data type.</p>

                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Create Series from list
s = pd.Series([1, 3, 5, 7, 9])
print(s)
# 0    1
# 1    3
# 2    5
# 3    7
# 4    9

# Series with custom index
s = pd.Series([1, 3, 5, 7, 9], index=['a', 'b', 'c', 'd', 'e'])
print(s)
# a    1
# b    3
# c    5
# d    7
# e    9

# Create from dictionary
data = {'a': 1, 'b': 2, 'c': 3}
s = pd.Series(data)
print(s)

# Accessing elements
print(s['a'])     # 1
print(s[0])       # 1
print(s[['a', 'c']])  # Multiple elements

# Series operations
print(s + 10)     # Add 10 to all elements
print(s * 2)      # Multiply all by 2
print(s[s > 1])   # Filter values > 1</code></pre>
                </div>
            </section>

            <section id="dataframes" class="card">
                <h2>4. DataFrames</h2>
                <p>A DataFrame is a 2-dimensional labeled data structure with columns of potentially different types.</p>

                <h3>Creating DataFrames</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># From dictionary
data = {
    'Name': ['Alice', 'Bob', 'Charlie', 'David'],
    'Age': [25, 30, 35, 40],
    'City': ['New York', 'London', 'Paris', 'Tokyo']
}
df = pd.DataFrame(data)
print(df)
#       Name  Age      City
# 0    Alice   25  New York
# 1      Bob   30    London
# 2  Charlie   35     Paris
# 3    David   40     Tokyo

# From list of lists
data = [
    ['Alice', 25, 'New York'],
    ['Bob', 30, 'London'],
    ['Charlie', 35, 'Paris']
]
df = pd.DataFrame(data, columns=['Name', 'Age', 'City'])

# From NumPy array
arr = np.array([[1, 2, 3], [4, 5, 6]])
df = pd.DataFrame(arr, columns=['A', 'B', 'C'])

# Basic info
print(df.shape)      # (4, 3) - rows, columns
print(df.columns)    # Column names
print(df.index)      # Row indices
print(df.dtypes)     # Data types
print(df.info())     # Summary info</code></pre>
                </div>
            </section>

            <section id="reading" class="card">
                <h2>5. Reading Data</h2>
                <p>Pandas can read data from various file formats.</p>

                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Read CSV
df = pd.read_csv('data.csv')

# Read with specific options
df = pd.read_csv('data.csv',
                 sep=',',           # Delimiter
                 header=0,          # Row number to use as column names
                 index_col=0,       # Column to use as row labels
                 na_values=['NA', 'missing'])  # Values to treat as NaN

# Read Excel
df = pd.read_excel('data.xlsx', sheet_name='Sheet1')

# Read JSON
df = pd.read_json('data.json')

# Read from SQL database
import sqlite3
conn = sqlite3.connect('database.db')
df = pd.read_sql_query("SELECT * FROM table_name", conn)

# Read from URL
url = 'https://example.com/data.csv'
df = pd.read_csv(url)</code></pre>
                </div>
            </section>

            <section id="viewing" class="card">
                <h2>6. Viewing and Inspecting Data</h2>

                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># View first/last rows
print(df.head())      # First 5 rows
print(df.head(10))    # First 10 rows
print(df.tail())      # Last 5 rows

# Quick statistics
print(df.describe())  # Summary statistics
print(df.info())      # DataFrame info

# Shape and size
print(df.shape)       # (rows, columns)
print(df.size)        # Total elements
print(len(df))        # Number of rows

# Check for missing values
print(df.isnull().sum())      # Count nulls per column
print(df.notnull().sum())     # Count non-nulls

# Unique values
print(df['City'].unique())     # Unique values in column
print(df['City'].nunique())    # Count unique values
print(df['City'].value_counts())  # Frequency of each value

# Column information
print(df.columns.tolist())     # List of column names
print(df.dtypes)               # Data types of columns</code></pre>
                </div>
            </section>

            <section id="selection" class="card">
                <h2>7. Selection and Indexing</h2>

                <h3>Selecting Columns</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Single column (returns Series)
ages = df['Age']
print(ages)

# Multiple columns (returns DataFrame)
subset = df[['Name', 'Age']]
print(subset)

# Add new column
df['Salary'] = [50000, 60000, 70000, 80000]

# Delete column
df = df.drop('City', axis=1)  # axis=1 for columns
# or
del df['City']</code></pre>
                </div>

                <h3>Selecting Rows</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Select by position with iloc
print(df.iloc[0])         # First row
print(df.iloc[0:3])       # First 3 rows
print(df.iloc[0:3, 0:2])  # First 3 rows, first 2 columns

# Select by label with loc
df = df.set_index('Name')
print(df.loc['Alice'])            # Row with index 'Alice'
print(df.loc['Alice':'Charlie'])  # Rows from Alice to Charlie
print(df.loc['Alice', 'Age'])     # Specific cell

# Boolean indexing
print(df.iloc[[0, 2]])    # Rows 0 and 2</code></pre>
                </div>
            </section>

            <section id="filtering" class="card">
                <h2>8. Filtering Data</h2>

                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Single condition
df_filtered = df[df['Age'] > 30]
print(df_filtered)

# Multiple conditions (AND)
df_filtered = df[(df['Age'] > 25) & (df['Salary'] > 55000)]

# Multiple conditions (OR)
df_filtered = df[(df['Age'] < 30) | (df['City'] == 'Tokyo')]

# Using isin()
cities = ['New York', 'London']
df_filtered = df[df['City'].isin(cities)]

# Using query() method
df_filtered = df.query('Age > 30 and Salary < 75000')

# Filter by string methods
df_filtered = df[df['Name'].str.startswith('A')]
df_filtered = df[df['Name'].str.contains('li')]

# Not null filtering
df_filtered = df[df['Age'].notnull()]</code></pre>
                </div>
            </section>

            <section id="operations" class="card">
                <h2>9. Data Operations</h2>

                <h3>Sorting</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Sort by column
df_sorted = df.sort_values('Age')
df_sorted = df.sort_values('Age', ascending=False)

# Sort by multiple columns
df_sorted = df.sort_values(['City', 'Age'])

# Sort index
df_sorted = df.sort_index()</code></pre>
                </div>

                <h3>Adding and Modifying Columns</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Add new column from calculation
df['Age_in_10_years'] = df['Age'] + 10

# Add column from condition
df['Senior'] = df['Age'] > 35

# Modify existing column
df['Age'] = df['Age'] + 1

# Rename columns
df = df.rename(columns={'Age': 'Years', 'City': 'Location'})

# Drop duplicates
df = df.drop_duplicates()
df = df.drop_duplicates(subset=['Name'])  # Based on specific column</code></pre>
                </div>

                <h3>String Operations</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Convert case
df['Name'] = df['Name'].str.upper()
df['Name'] = df['Name'].str.lower()
df['Name'] = df['Name'].str.title()

# String methods
df['Name'].str.len()              # Length of strings
df['Name'].str.strip()            # Remove whitespace
df['Name'].str.replace('A', 'a')  # Replace characters
df['Name'].str.split(' ')         # Split strings

# Extract patterns
df['City'].str.extract(r'([A-Z][a-z]+)')  # Regex extraction</code></pre>
                </div>
            </section>

            <section id="grouping" class="card">
                <h2>10. GroupBy Operations</h2>
                <p>Group data and perform aggregate operations.</p>

                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Basic groupby
grouped = df.groupby('City')

# Aggregate functions
print(df.groupby('City')['Age'].mean())
print(df.groupby('City')['Salary'].sum())
print(df.groupby('City').size())  # Count per group

# Multiple aggregations
print(df.groupby('City').agg({
    'Age': ['mean', 'min', 'max'],
    'Salary': ['sum', 'mean']
}))

# Group by multiple columns
df.groupby(['City', 'Department']).mean()

# Apply custom function to groups
def age_range(x):
    return x.max() - x.min()

df.groupby('City')['Age'].apply(age_range)

# Iterate through groups
for name, group in df.groupby('City'):
    print(f"\n{name}:")
    print(group)</code></pre>
                </div>
            </section>

            <section id="merging" class="card">
                <h2>11. Merging and Joining</h2>

                <h3>Concatenation</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Vertical concatenation (stack rows)
df1 = pd.DataFrame({'A': [1, 2], 'B': [3, 4]})
df2 = pd.DataFrame({'A': [5, 6], 'B': [7, 8]})
result = pd.concat([df1, df2], ignore_index=True)

# Horizontal concatenation (stack columns)
result = pd.concat([df1, df2], axis=1)

# Concatenate with keys
result = pd.concat([df1, df2], keys=['first', 'second'])</code></pre>
                </div>

                <h3>Merging (SQL-style joins)</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python">df1 = pd.DataFrame({
    'key': ['A', 'B', 'C'],
    'value1': [1, 2, 3]
})

df2 = pd.DataFrame({
    'key': ['A', 'B', 'D'],
    'value2': [4, 5, 6]
})

# Inner join (default)
result = pd.merge(df1, df2, on='key')
# Only keeps rows where key exists in both

# Left join
result = pd.merge(df1, df2, on='key', how='left')
# Keeps all rows from df1

# Right join
result = pd.merge(df1, df2, on='key', how='right')
# Keeps all rows from df2

# Outer join
result = pd.merge(df1, df2, on='key', how='outer')
# Keeps all rows from both

# Merge on multiple columns
result = pd.merge(df1, df2, on=['key1', 'key2'])

# Merge with different column names
result = pd.merge(df1, df2, left_on='key1', right_on='key2')</code></pre>
                </div>
            </section>

            <section id="missing" class="card">
                <h2>12. Handling Missing Data</h2>

                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Check for missing values
print(df.isnull())           # Boolean DataFrame
print(df.isnull().sum())     # Count per column
print(df.isnull().any())     # Any nulls per column

# Drop missing values
df_clean = df.dropna()                 # Drop rows with any null
df_clean = df.dropna(axis=1)           # Drop columns with any null
df_clean = df.dropna(how='all')        # Drop only if all values are null
df_clean = df.dropna(subset=['Age'])   # Drop based on specific column

# Fill missing values
df_filled = df.fillna(0)                      # Fill with 0
df_filled = df.fillna(df.mean())              # Fill with mean
df_filled = df.fillna(method='ffill')         # Forward fill
df_filled = df.fillna(method='bfill')         # Backward fill

# Fill specific column
df['Age'] = df['Age'].fillna(df['Age'].mean())

# Interpolate missing values
df['Age'] = df['Age'].interpolate()

# Replace specific values
df = df.replace(0, np.nan)                    # Replace 0 with NaN
df = df.replace([0, -1], np.nan)              # Replace multiple values</code></pre>
                </div>
            </section>

            <section id="apply" class="card">
                <h2>13. Apply Functions</h2>
                <p>Apply custom functions to DataFrames and Series.</p>

                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Apply to Series
def double(x):
    return x * 2

df['Age_doubled'] = df['Age'].apply(double)

# Lambda function
df['Age_squared'] = df['Age'].apply(lambda x: x ** 2)

# Apply to DataFrame rows (axis=1)
def calculate_bonus(row):
    if row['Age'] > 35:
        return row['Salary'] * 0.1
    else:
        return row['Salary'] * 0.05

df['Bonus'] = df.apply(calculate_bonus, axis=1)

# Apply to DataFrame columns (axis=0)
df_normalized = df[['Age', 'Salary']].apply(lambda x: (x - x.min()) / (x.max() - x.min()))

# Map values (for Series)
age_category = {
    25: 'Young',
    30: 'Mid',
    35: 'Senior',
    40: 'Senior'
}
df['Category'] = df['Age'].map(age_category)

# Replace with mapping
df['City'] = df['City'].replace({
    'New York': 'NY',
    'Los Angeles': 'LA'
})

# applymap (element-wise on entire DataFrame)
df_rounded = df[['Age', 'Salary']].applymap(lambda x: round(x, 2))</code></pre>
                </div>
            </section>

            <section id="time-series" class="card">
                <h2>14. Time Series</h2>
                <p>Working with dates, times, and time-indexed data.</p>

                <h3>Creating Date Ranges</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Date range
dates = pd.date_range('2023-01-01', periods=10, freq='D')
print(dates)

# Different frequencies
dates = pd.date_range('2023-01-01', periods=12, freq='M')   # Month
dates = pd.date_range('2023-01-01', periods=52, freq='W')   # Week
dates = pd.date_range('2023-01-01', periods=24, freq='H')   # Hour

# Create DataFrame with date index
df = pd.DataFrame({
    'value': np.random.randn(10)
}, index=dates)</code></pre>
                </div>

                <h3>Date Operations</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Convert string to datetime
df['date'] = pd.to_datetime(df['date_string'])

# Parse with specific format
df['date'] = pd.to_datetime(df['date_string'], format='%Y-%m-%d')

# Extract date components
df['year'] = df['date'].dt.year
df['month'] = df['date'].dt.month
df['day'] = df['date'].dt.day
df['day_name'] = df['date'].dt.day_name()
df['week'] = df['date'].dt.isocalendar().week

# Filter by date
df_filtered = df[df['date'] > '2023-01-01']
df_filtered = df[(df['date'] >= '2023-01-01') & (df['date'] <= '2023-12-31')]

# Set date as index
df = df.set_index('date')

# Resample time series data
df_monthly = df.resample('M').mean()      # Monthly average
df_weekly = df.resample('W').sum()        # Weekly sum

# Rolling window calculations
df['rolling_mean'] = df['value'].rolling(window=7).mean()
df['rolling_sum'] = df['value'].rolling(window=7).sum()

# Shift data (for lag features)
df['previous_value'] = df['value'].shift(1)
df['next_value'] = df['value'].shift(-1)</code></pre>
                </div>
            </section>

            <section id="export" class="card">
                <h2>15. Exporting Data</h2>
                <p>Save DataFrames to various file formats.</p>

                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Export to CSV
df.to_csv('output.csv', index=False)
df.to_csv('output.csv', index=False, sep=';')  # Custom separator

# Export to Excel
df.to_excel('output.xlsx', sheet_name='Data', index=False)

# Multiple sheets
with pd.ExcelWriter('output.xlsx') as writer:
    df1.to_excel(writer, sheet_name='Sheet1', index=False)
    df2.to_excel(writer, sheet_name='Sheet2', index=False)

# Export to JSON
df.to_json('output.json')
df.to_json('output.json', orient='records')  # List of records

# Export to SQL
from sqlalchemy import create_engine
engine = create_engine('sqlite:///database.db')
df.to_sql('table_name', engine, if_exists='replace', index=False)
# if_exists options: 'fail', 'replace', 'append'

# Export to HTML
df.to_html('output.html')

# Export to pickle (preserves data types)
df.to_pickle('output.pkl')

# Read pickle
df = pd.read_pickle('output.pkl')</code></pre>
                </div>

                <h3>Advanced Export Options</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Export specific columns
df[['Name', 'Age']].to_csv('subset.csv', index=False)

# Export with compression
df.to_csv('output.csv.gz', compression='gzip', index=False)

# Export with encoding
df.to_csv('output.csv', encoding='utf-8', index=False)

# Export to clipboard (for quick paste)
df.to_clipboard(index=False)</code></pre>
                </div>
            </section>

            <section class="card">
                <h2>Bonus: Common Pandas Patterns</h2>

                <h3>Chaining Operations</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Method chaining for clean code
result = (df
    .query('Age > 25')
    .groupby('City')['Salary']
    .mean()
    .sort_values(ascending=False)
    .head(5)
)

# Pipeline approach
result = (df
    .assign(Bonus=lambda x: x['Salary'] * 0.1)
    .query('Bonus > 5000')
    .sort_values('Bonus', ascending=False)
)</code></pre>
                </div>

                <h3>Pivot Tables</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Create pivot table
pivot = df.pivot_table(
    values='Salary',
    index='City',
    columns='Department',
    aggfunc='mean'
)

# Multiple aggregations
pivot = df.pivot_table(
    values='Salary',
    index='City',
    columns='Department',
    aggfunc=['mean', 'sum', 'count']
)

# Melt (unpivot)
melted = df.melt(
    id_vars=['Name'],
    value_vars=['Age', 'Salary'],
    var_name='Metric',
    value_name='Value'
)</code></pre>
                </div>

                <h3>Cross Tabulation</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Frequency table
crosstab = pd.crosstab(df['City'], df['Department'])

# With percentages
crosstab = pd.crosstab(
    df['City'],
    df['Department'],
    normalize='index'  # Row percentages
)

# With margins (totals)
crosstab = pd.crosstab(
    df['City'],
    df['Department'],
    margins=True
)</code></pre>
                </div>

                <h3>Window Functions</h3>
                <div class="code-container">
                    <div class="code-header">
                        <span>Python</span>
                        <button class="copy-btn">Copy</button>
                    </div>
                    <pre><code class="language-python"># Ranking
df['rank'] = df['Salary'].rank(ascending=False)
df['rank'] = df.groupby('City')['Salary'].rank(ascending=False)

# Cumulative operations
df['cumsum'] = df['Salary'].cumsum()
df['cummax'] = df['Salary'].cummax()

# Percent change
df['pct_change'] = df['Salary'].pct_change()

# Expanding window (cumulative statistics)
df['expanding_mean'] = df['Salary'].expanding().mean()</code></pre>
                </div>
            </section>

            <div class="card" style="text-align: center; background: linear-gradient(135deg, rgba(102, 126, 234, 0.1), rgba(118, 75, 162, 0.1));">
                <h2>🎉 Congratulations!</h2>
                <p style="font-size: 1.2rem; margin-bottom: 30px;">You've mastered Pandas fundamentals! Ready to query databases with SQL?</p>
                <div style="display: flex; gap: 20px; justify-content: center; flex-wrap: wrap;">
                    <a href="sql-notes.html" style="background: linear-gradient(135deg, #667eea, #764ba2); color: white; padding: 15px 30px; border-radius: 12px; font-weight: 600; transition: transform 0.3s; text-decoration: none;">Next: SQL →</a>
                    <a href="numpy-notes.html" style="background: rgba(102, 126, 234, 0.2); color: #667eea; padding: 15px 30px; border-radius: 12px; font-weight: 600; transition: transform 0.3s; text-decoration: none;">← Back to NumPy</a>
                    <a href="index.html" style="background: rgba(102, 126, 234, 0.2); color: #667eea; padding: 15px 30px; border-radius: 12px; font-weight: 600; transition: transform 0.3s; text-decoration: none;">🏠 Home</a>
                </div>
            </div>
        </main>
    </div>
    <footer class="footer">
        <div class="footer-container">
            <div class="footer-section">
                <h3>📚 Learning Hub</h3>
                <p>A comprehensive platform for mastering data science fundamentals. Built with passion for learners everywhere.</p>
                <div class="social-links">
                    <a href="https://github.com/Developer-Sahil/" title="GitHub">💻</a>
                    <a href="https://www.linkedin.com/in/sahil-sharma-921969239/" title="LinkedIn">💼</a>
                    <!-- <a href="#" title="Twitter">🐦</a> -->
                    <a href="[email protected]" title="Email">📧</a>
                </div>
            </div>

            <div class="footer-section">
                <h3>🎓 Topics</h3>
                <ul>
                    <li><a href="python-notes.html">Python Basics</a></li>
                    <li><a href="numpy-notes.html">NumPy</a></li>
                    <li><a href="pandas-notes.html">Pandas</a></li>
                    <li><a href="sql-notes.html">SQL</a></li>
                    <li><a href="statistics-notes.html">Statistics</a></li>
                </ul>
            </div>

            <div class="footer-section">
                <h3>🔗 Quick Links</h3>
                <ul>
                    <li><a href="index.html">Home</a></li>
                    <li><a href="about.html">About Me</a></li>
                    <li><a href="#" onclick="window.scrollTo({top: 0, behavior: 'smooth'}); return false;">Back to Top</a></li>
                </ul>
            </div>

            <div class="footer-section">
                <h3>💡 Resources</h3>
                <ul>
                    <li><a href="https://docs.python.org/" target="_blank">Python Docs</a></li>
                    <li><a href="https://numpy.org/doc/" target="_blank">NumPy Docs</a></li>
                    <li><a href="https://pandas.pydata.org/docs/" target="_blank">Pandas Docs</a></li>
                    <li><a href="https://www.w3schools.com/sql/" target="_blank">SQL Tutorial</a></li>
                </ul>
            </div>
        </div>

        <div class="footer-bottom">
            <p>&copy; 2025 Data Science Learning Hub. Built by Sahil Sharma for learners everywhere.</p>
            <p>Open source educational project • <a href="about.html">Learn more about the creator</a></p>
        </div>
    </footer>

    <script src="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/prism.min.js"></script>
    <script src="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/components/prism-python.min.js"></script>
    <script src="https://cdnjs.cloudflare.com/ajax/libs/prism/1.29.0/components/prism-bash.min.js"></script>

    <script src="js/common.js"></script>
    <script src="js/notes.js"></script>
</body>
</html>