File size: 8,175 Bytes
ed72aac |
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 |
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "0r5hCx60Yv0u"
},
"outputs": [],
"source": [
"import pandas as pd\n"
]
},
{
"cell_type": "code",
"source": [
"#2. Reading a CSV File"
],
"metadata": {
"id": "dytrA9JLZJaO"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import pandas as pd\n",
"\n",
"try:\n",
" # Read the CSV file into a DataFrame\n",
" df = pd.read_csv(r\"/content/sample_data (1).csv\")\n",
" print(df)\n",
"except FileNotFoundError:\n",
" print(\"Error: The file was not found.\")\n",
"except pd.errors.ParserError:\n",
" print(\"Error: There was a problem parsing the CSV file.\")\n",
"except Exception as e:\n",
" print(f\"An unexpected error occurred: {e}\")\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "33v8Kr5LeNYP",
"outputId": "2d8e6eef-a25e-4c31-deab-80d4d6da35b8"
},
"execution_count": 18,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" ID Name Age Gender City Salary\n",
"0 1 Alice 25 Female New York 70000\n",
"1 2 Bob 30 Male Los Angeles 80000\n",
"2 3 Charlie 35 Male Chicago 90000\n",
"3 4 Diana 28 Female Houston 75000\n",
"4 5 Edward 40 Male San Francisco 100000\n",
"5 6 Faith 32 Female Miami 82000\n",
"6 7 George 45 Male Seattle 110000\n",
"7 8 Hannah 29 Female Boston 72000\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"import csv\n",
"\n",
"# Path to your CSV file\n",
"csv_file_path = 'employee_data.csv'\n",
"\n",
"# Function to read CSV using csv module\n",
"def read_csv_using_csv_module():\n",
" try:\n",
" with open(r\"/content/sample_data (1).csv\") as file:\n",
" csv_reader = csv.DictReader(file) # Use DictReader to access columns by name\n",
" print(\"Reading using csv module:\")\n",
" for row in csv_reader:\n",
" try:\n",
" # Ensuring data types are correct (Age should be an integer, Salary should be numeric)\n",
" row['Age'] = int(row['Age']) # Convert Age to integer\n",
" row['Salary'] = float(row['Salary']) # Convert Salary to float\n",
" print(row)\n",
" except ValueError as ve:\n",
" print(f\"Error: Invalid data type in row {row}. Error: {ve}\")\n",
" except FileNotFoundError:\n",
" print(\"Error: The file was not found.\")\n",
" except csv.Error as e:\n",
" print(f\"Error reading the CSV file with csv module: {e}\")\n",
" except Exception as e:\n",
" print(f\"An unexpected error occurred with csv module: {e}\")\n",
"\n",
"# Call the function to read using csv module\n",
"read_csv_using_csv_module()\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "xvRO2NmZkCPJ",
"outputId": "abdb3575-5522-42d2-96d2-69231b60b6a7"
},
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Reading using csv module:\n",
"{'ID': '1', 'Name': 'Alice', 'Age': 25, 'Gender': 'Female', 'City': 'New York', 'Salary': 70000.0}\n",
"{'ID': '2', 'Name': 'Bob', 'Age': 30, 'Gender': 'Male', 'City': 'Los Angeles', 'Salary': 80000.0}\n",
"{'ID': '3', 'Name': 'Charlie', 'Age': 35, 'Gender': 'Male', 'City': 'Chicago', 'Salary': 90000.0}\n",
"{'ID': '4', 'Name': 'Diana', 'Age': 28, 'Gender': 'Female', 'City': 'Houston', 'Salary': 75000.0}\n",
"{'ID': '5', 'Name': 'Edward', 'Age': 40, 'Gender': 'Male', 'City': 'San Francisco', 'Salary': 100000.0}\n",
"{'ID': '6', 'Name': 'Faith', 'Age': 32, 'Gender': 'Female', 'City': 'Miami', 'Salary': 82000.0}\n",
"{'ID': '7', 'Name': 'George', 'Age': 45, 'Gender': 'Male', 'City': 'Seattle', 'Salary': 110000.0}\n",
"{'ID': '8', 'Name': 'Hannah', 'Age': 29, 'Gender': 'Female', 'City': 'Boston', 'Salary': 72000.0}\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Using pandas for Reading and Handling Errors"
],
"metadata": {
"id": "oXkmSf5lkjiP"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import pandas as pd\n",
"\n",
"# Path to your CSV file\n",
"csv_file_path = r\"/content/sample_data (1).csv\"\n",
"\n",
"# Function to read CSV using pandas\n",
"def read_csv_using_pandas():\n",
" try:\n",
" # Read the CSV file into a pandas DataFrame\n",
" df = pd.read_csv(r\"/content/sample_data (1).csv\")\n",
" print(\"\\nReading using pandas:\")\n",
"\n",
" # Ensure that the 'Age' and 'Salary' columns are correctly typed\n",
" df['Age'] = pd.to_numeric(df['Age'], errors='raise') # Ensures Age is numeric\n",
" df['Salary'] = pd.to_numeric(df['Salary'], errors='raise') # Ensures Salary is numeric\n",
"\n",
" # Display the DataFrame\n",
" print(df)\n",
"\n",
" except FileNotFoundError:\n",
" print(\"Error: The file was not found.\")\n",
" except pd.errors.ParserError:\n",
" print(\"Error: There was a problem parsing the CSV file with pandas.\")\n",
" except ValueError as ve:\n",
" print(f\"Error: Invalid data type in the CSV file. {ve}\")\n",
" except Exception as e:\n",
" print(f\"An unexpected error occurred with pandas: {e}\")\n",
"\n",
"# Call the function to read using pandas\n",
"read_csv_using_pandas()\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "SItXSSqbkpKr",
"outputId": "9e6c4168-bc01-49d8-eabd-18dacab7e3c9"
},
"execution_count": 21,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
"Reading using pandas:\n",
" ID Name Age Gender City Salary\n",
"0 1 Alice 25 Female New York 70000\n",
"1 2 Bob 30 Male Los Angeles 80000\n",
"2 3 Charlie 35 Male Chicago 90000\n",
"3 4 Diana 28 Female Houston 75000\n",
"4 5 Edward 40 Male San Francisco 100000\n",
"5 6 Faith 32 Female Miami 82000\n",
"6 7 George 45 Male Seattle 110000\n",
"7 8 Hannah 29 Female Boston 72000\n"
]
}
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "L0TGXiLsk0yi"
},
"execution_count": null,
"outputs": []
}
]
} |