Spaces:
Running
Running
File size: 3,568 Bytes
fb1a11c |
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 |
{
"notebook_title": "Exploratory data analysis (EDA)",
"notebook_type": "eda",
"dataset_type": "numeric",
"notebook_template": [
{
"cell_type": "markdown",
"source": "\n---\n# **Exploratory Data Analysis (EDA) Notebook for {dataset_name} dataset**\n---\n"
},
{
"cell_type": "markdown",
"source": "## 1. Setup necessary libraries and load the dataset"
},
{
"cell_type": "code",
"source": "\n# Install and import necessary libraries.\n!pip install pandas matplotlib seaborn\n"
},
{
"cell_type": "code",
"source": "\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n"
},
{
"cell_type": "code",
"source": "\n# Load the dataset as a DataFrame\n{first_code}\n"
},
{
"cell_type": "markdown",
"source": "## 2. Understanding the Dataset"
},
{
"cell_type": "code",
"source": "\n# First rows of the dataset and info\nprint(df.head())\nprint(df.info())\n"
},
{
"cell_type": "code",
"source": "\n# Check for missing values\nprint(df.isnull().sum())\n"
},
{
"cell_type": "code",
"source": "\n# Identify data types of each column\nprint(df.dtypes)\n"
},
{
"cell_type": "code",
"source": "\n# Detect duplicated rows\nprint(df.duplicated().sum())\n"
},
{
"cell_type": "code",
"source": "\n# Generate descriptive statistics\nprint(df.describe())\n"
},
{
"type": "categoric",
"cell_type": "code",
"source": "\n# Unique values in categorical columns\ndf.select_dtypes(include=['object']).nunique()\n"
},
{
"cell_type": "markdown",
"source": "## 3. Data Visualization"
},
{
"type": "numeric",
"cell_type": "code",
"source": "\n# Correlation matrix for numerical columns\ncorr_matrix = df.corr(numeric_only=True)\nplt.figure(figsize=(10, 8))\nsns.heatmap(corr_matrix, annot=True, fmt='.2f', cmap='coolwarm', square=True)\nplt.title('Correlation Matrix')\nplt.show()\n"
},
{
"type": "numeric",
"cell_type": "code",
"source": "\n# Distribution plots for numerical columns\nfor column in df.select_dtypes(include=['int64', 'float64']).columns:\n plt.figure(figsize=(8, 4))\n sns.histplot(df[column], kde=True)\n plt.title(f'Distribution of {column}')\n plt.xlabel(column)\n plt.ylabel('Frequency')\n plt.show()\n"
},
{
"type": "categoric",
"cell_type": "code",
"source": "\n# Count plots for categorical columns\nfor column in df.select_dtypes(include=['object']).columns:\n plt.figure(figsize=(8, 4))\n sns.countplot(x=column, data=df)\n plt.title(f'Count Plot of {column}')\n plt.xlabel(column)\n plt.ylabel('Count')\n plt.show()\n"
},
{
"type": "numeric",
"cell_type": "code",
"source": "\n# Box plots for detecting outliers in numerical columns\nfor column in df.select_dtypes(include=['int64', 'float64']).columns:\n plt.figure(figsize=(8, 4))\n sns.boxplot(df[column])\n plt.title(f'Box Plot of {column}')\n plt.xlabel(column)\n plt.show()\n"
}
]
} |