Spaces:
Running
Running
| import streamlit as st | |
| import pandas as pd | |
| import numpy as np | |
| import io | |
| from sklearn import datasets | |
| def load_example_data(dataset_name): | |
| """ | |
| Load example datasets for demonstration | |
| Parameters: | |
| ----------- | |
| dataset_name : str | |
| Name of the example dataset to load | |
| Returns: | |
| -------- | |
| DataFrame: The loaded dataset as a pandas DataFrame | |
| """ | |
| if dataset_name == "iris": | |
| data = datasets.load_iris() | |
| df = pd.DataFrame(data.data, columns=data.feature_names) | |
| df['species'] = pd.Categorical.from_codes(data.target, data.target_names) | |
| return df | |
| elif dataset_name == "boston": | |
| data = datasets.fetch_openml(name='boston', version=1, as_frame=True) | |
| return data.frame | |
| elif dataset_name == "titanic": | |
| data = datasets.fetch_openml(name='titanic', version=1, as_frame=True) | |
| return data.frame | |
| elif dataset_name == "wine": | |
| data = datasets.load_wine() | |
| df = pd.DataFrame(data.data, columns=data.feature_names) | |
| df['wine_type'] = pd.Categorical.from_codes(data.target, data.target_names) | |
| return df | |
| return None | |
| def display_dataset_info(df): | |
| """Display information about the dataset.""" | |
| st.subheader("Dataset Information") | |
| # Basic info | |
| st.markdown(f"**Rows:** {df.shape[0]}") | |
| st.markdown(f"**Columns:** {df.shape[1]}") | |
| # Missing values | |
| missing_values = df.isnull().sum().sum() | |
| st.markdown(f"**Missing Values:** {missing_values}") | |
| # Data types overview | |
| dtypes = df.dtypes.value_counts().to_dict() | |
| st.markdown("**Data Types:**") | |
| for dtype, count in dtypes.items(): | |
| st.markdown(f"- {dtype}: {count} columns") | |
| # Basic statistics | |
| st.subheader("Summary Statistics") | |
| numeric_cols = df.select_dtypes(include=['int64', 'float64']).columns | |
| if len(numeric_cols) > 0: | |
| st.dataframe(df[numeric_cols].describe(), use_container_width=True) | |
| else: | |
| st.info("No numeric columns found for summary statistics.") | |
| def get_numeric_columns(df): | |
| """Return list of numeric columns in the dataframe.""" | |
| return df.select_dtypes(include=['int64', 'float64']).columns.tolist() | |
| def get_categorical_columns(df): | |
| """Return list of categorical columns in the dataframe.""" | |
| return df.select_dtypes(include=['object', 'category', 'bool']).columns.tolist() | |
| def get_datetime_columns(df): | |
| """Return list of datetime columns in the dataframe.""" | |
| return df.select_dtypes(include=['datetime64']).columns.tolist() | |
| def filter_dataframe(df, column_filters): | |
| """ | |
| Filter dataframe based on provided filters | |
| Parameters: | |
| ----------- | |
| df : pandas.DataFrame | |
| DataFrame to filter | |
| column_filters : dict | |
| Dictionary of column names and filter values | |
| Returns: | |
| -------- | |
| pandas.DataFrame: Filtered dataframe | |
| """ | |
| filtered_df = df.copy() | |
| for column, filter_value in column_filters.items(): | |
| if filter_value: | |
| if column in get_numeric_columns(df): | |
| min_val, max_val = filter_value | |
| filtered_df = filtered_df[(filtered_df[column] >= min_val) & | |
| (filtered_df[column] <= max_val)] | |
| elif column in get_categorical_columns(df): | |
| if not isinstance(filter_value, list): | |
| filter_value = [filter_value] | |
| filtered_df = filtered_df[filtered_df[column].isin(filter_value)] | |
| return filtered_df | |
| def download_dataframe(df, filename="data.csv"): | |
| """ | |
| Generate a download link for the dataframe | |
| Parameters: | |
| ----------- | |
| df : pandas.DataFrame | |
| DataFrame to download | |
| filename : str | |
| Filename for download | |
| Returns: | |
| -------- | |
| str: HTML link for download | |
| """ | |
| csv = df.to_csv(index=False) | |
| b64 = io.StringIO() | |
| b64.write(csv) | |
| return b64.getvalue() | |
| def explain_correlation(): | |
| """Return educational text about correlation.""" | |
| return """ | |
| ### Understanding Correlation | |
| Correlation measures the statistical relationship between two variables. The correlation coefficient ranges from -1 to 1: | |
| - **1**: Perfect positive correlation (as one variable increases, the other increases) | |
| - **0**: No correlation (variables are not related) | |
| - **-1**: Perfect negative correlation (as one variable increases, the other decreases) | |
| **Interpreting correlation strength:** | |
| - 0.00-0.19: Very weak | |
| - 0.20-0.39: Weak | |
| - 0.40-0.59: Moderate | |
| - 0.60-0.79: Strong | |
| - 0.80-1.00: Very strong | |
| **Important note:** Correlation does not imply causation. Two variables may be correlated without one causing the other. | |
| """ | |
| def explain_hypothesis_testing(): | |
| """Return educational text about hypothesis testing.""" | |
| return """ | |
| ### Understanding Hypothesis Testing | |
| Hypothesis testing is a statistical method to make decisions about a population based on sample data. | |
| **Key components:** | |
| 1. **Null hypothesis (H₀)**: Assumes no effect or no difference (status quo) | |
| 2. **Alternative hypothesis (H₁)**: Contradicts the null hypothesis | |
| 3. **p-value**: Probability of observing results at least as extreme as the current data, assuming H₀ is true | |
| 4. **Significance level (α)**: Threshold for rejecting H₀ (commonly 0.05) | |
| **Decision rule:** If p-value < α, reject H₀ | |
| **Common tests:** | |
| - **t-test**: Compares means between groups | |
| - **ANOVA**: Compares means across multiple groups | |
| - **Chi-square**: Tests relationships between categorical variables | |
| """ | |
| def explain_data_cleaning(): | |
| """Return educational text about data cleaning.""" | |
| return """ | |
| ### Data Cleaning Basics | |
| Data cleaning is an essential step in the data science workflow. Clean data leads to more accurate analysis and models. | |
| **Common data issues:** | |
| 1. **Missing values**: Data points that are not recorded | |
| 2. **Duplicates**: Identical records that can skew analysis | |
| 3. **Outliers**: Extreme values that may or may not represent errors | |
| 4. **Inconsistent formats**: Dates, currencies, or text in different formats | |
| 5. **Data type issues**: Numbers stored as text, etc. | |
| **Common cleaning approaches:** | |
| - **Missing data**: Remove or impute with mean, median, or predicted values | |
| - **Outliers**: Remove, transform, or analyze separately | |
| - **Standardization**: Convert data to consistent formats and scales | |
| """ | |
| def explain_machine_learning(): | |
| """Return educational text about machine learning basics.""" | |
| return """ | |
| ### Machine Learning Fundamentals | |
| Machine learning algorithms learn patterns from data to make predictions or decisions without being explicitly programmed. | |
| **Main types of machine learning:** | |
| 1. **Supervised Learning**: Learn from labeled data to predict outcomes | |
| - **Classification**: Predict categories (e.g., spam detection) | |
| - **Regression**: Predict continuous values (e.g., house prices) | |
| 2. **Unsupervised Learning**: Find patterns in unlabeled data | |
| - **Clustering**: Group similar data points (e.g., customer segmentation) | |
| - **Dimensionality Reduction**: Simplify data while preserving information | |
| 3. **Reinforcement Learning**: Learn through trial and error with rewards/penalties | |
| **Machine Learning Workflow:** | |
| 1. Data preparation (cleaning, feature engineering) | |
| 2. Model selection and training | |
| 3. Evaluation (using metrics like accuracy, precision, recall) | |
| 4. Deployment and monitoring | |
| """ | |