File size: 6,778 Bytes
854c114
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "cells": [
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "# Python Library Practice: Pandas\n",
                "\n",
                "Pandas is the primary tool for data manipulation and analysis in Python. It provides data structures like `DataFrame` and `Series` that make working with tabular data easy.\n",
                "\n",
                "### Resources:\n",
                "Refer to the **[Feature Engineering Guide](https://aashishgarg13.github.io/DataScience/feature-engineering/)** on your hub for data cleaning and transformation concepts using Pandas.\n",
                "\n",
                "### Objectives:\n",
                "1. **DataFrame Creation**: Building dataframes from dictionaries.\n",
                "2. **Selection & Filtering**: Querying data.\n",
                "3. **Grouping & Aggregation**: Summarizing data.\n",
                "4. **Handling Missing Data**: Methods to clean datasets.\n",
                "\n",
                "---"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## 1. DataFrame Basics\n",
                "\n",
                "### Task 1: Create a DataFrame\n",
                "Create a DataFrame from a dictionary with columns: `Name`, `Age`, and `City` for 5 people."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "import pandas as pd\n",
                "\n",
                "# YOUR CODE HERE\n"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "<details>\n",
                "<summary><b>Click to see Solution</b></summary>\n",
                "\n",
                "```python\n",
                "data = {\n",
                "    'Name': ['Alice', 'Bob', 'Charlie', 'David', 'Eva'],\n",
                "    'Age': [24, 30, 22, 35, 29],\n",
                "    'City': ['NY', 'LA', 'Chicago', 'Houston', 'Miami']\n",
                "}\n",
                "df = pd.DataFrame(data)\n",
                "print(df)\n",
                "```\n",
                "</details>"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## 2. Selection and Filtering\n",
                "\n",
                "### Task 2: Conditional Selection\n",
                "Using the DataFrame from Task 1, select all rows where `Age` is greater than 25."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "# YOUR CODE HERE\n"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "<details>\n",
                "<summary><b>Click to see Solution</b></summary>\n",
                "\n",
                "```python\n",
                "filtered_df = df[df['Age'] > 25]\n",
                "print(filtered_df)\n",
                "```\n",
                "</details>"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## 3. GroupBy and Aggregation\n",
                "\n",
                "### Task 3: Grouping Data\n",
                "Create a DataFrame with `Category` and `Sales`. Group by `Category` and calculate the average `Sales`."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "sales_data = {\n",
                "    'Category': ['Electronics', 'Clothing', 'Electronics', 'Home', 'Clothing', 'Home'],\n",
                "    'Sales': [100, 50, 200, 300, 40, 150]\n",
                "}\n",
                "sales_df = pd.DataFrame(sales_data)\n",
                "\n",
                "# YOUR CODE HERE\n"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "<details>\n",
                "<summary><b>Click to see Solution</b></summary>\n",
                "\n",
                "```python\n",
                "result = sales_df.groupby('Category').mean()\n",
                "print(result)\n",
                "```\n",
                "</details>"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## 4. Merging and Joining\n",
                "\n",
                "### Task 4: Merge DataFrames\n",
                "Merge two DataFrames on a common `ID` column."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "df1 = pd.DataFrame({'ID': [1, 2, 3], 'Value1': ['A', 'B', 'C']})\n",
                "df2 = pd.DataFrame({'ID': [2, 3, 4], 'Value2': ['X', 'Y', 'Z']})\n",
                "\n",
                "# YOUR CODE HERE\n"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "<details>\n",
                "<summary><b>Click to see Solution</b></summary>\n",
                "\n",
                "```python\n",
                "merged = pd.merge(df1, df2, on='ID', how='inner')\n",
                "print(merged)\n",
                "```\n",
                "</details>"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "--- \n",
                "### Excellent Pandas Practice! \n",
                "You're becoming a data manipulator pro.\n",
                "Next: **Matplotlib & Seaborn Practice**."
            ]
        }
    ],
    "metadata": {
        "kernelspec": {
            "display_name": "Python 3",
            "language": "python",
            "name": "python3"
        },
        "language_info": {
            "codemirror_mode": {
                "name": "ipython",
                "version": 3
            },
            "file_extension": ".py",
            "mimetype": "text/x-python",
            "name": "python",
            "nbconvert_exporter": "python",
            "pygments_lexer": "ipython3",
            "version": "3.12.7"
        }
    },
    "nbformat": 4,
    "nbformat_minor": 4
}