Initial commit: FRED_ML project without binary files

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,78 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Virtual environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# Data files
+data/exports/*.png
+data/exports/*.jpg
+data/exports/*.jpeg
+data/exports/*.gif
+data/exports/*.svg
+data/exports/*.pdf
+data/processed/*.csv
+data/raw/*
+
+# Logs
+logs/*.log
+*.log
+
+# Model files
+*.pkl
+*.pickle
+*.joblib
+*.h5
+*.hdf5
+*.model
+
+# Temporary files
+*.tmp
+*.temp
+temp/
+tmp/ 

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Edwin Salguero
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,150 @@
+# FRED Economic Data Analysis Tool
+
+A comprehensive Python tool for collecting, analyzing, and visualizing Federal Reserve Economic Data (FRED) using the FRED API.
+
+## Features
+
+- **Data Collection**: Fetch economic indicators from FRED API
+- **Data Analysis**: Generate summary statistics and insights
+- **Visualization**: Create time series plots and charts
+- **Data Export**: Save data to CSV format
+- **Flexible Configuration**: Easy customization of indicators and date ranges
+
+## Setup
+
+### 1. Install Dependencies
+
+```bash
+pip install -r requirements.txt
+```
+
+### 2. API Key Configuration
+
+Your FRED API key is already configured in `config.py`:
+- API Key: `acf8bbec7efe3b6dfa6ae083e7152314`
+
+### 3. Project Structure
+
+```
+economic_output_datasets/
+├── config.py              # Configuration settings
+├── fred_data_collector.py # Main data collection script
+├── requirements.txt       # Python dependencies
+├── README.md             # This file
+├── data/                 # Output directory for CSV files
+└── plots/                # Output directory for visualizations
+```
+
+## Usage
+
+### Basic Usage
+
+Run the main script to collect and analyze economic data:
+
+```bash
+python fred_data_collector.py
+```
+
+This will:
+- Fetch data for key economic indicators (GDP, Unemployment Rate, CPI, Federal Funds Rate, 10-Year Treasury Rate)
+- Generate summary statistics
+- Create visualizations
+- Save data to CSV files
+
+### Custom Analysis
+
+You can customize the analysis by modifying the script:
+
+```python
+from fred_data_collector import FREDDataCollector
+
+# Initialize collector
+collector = FREDDataCollector()
+
+# Custom series and date range
+custom_series = ['GDP', 'UNRATE', 'CPIAUCSL']
+start_date = '2020-01-01'
+end_date = '2024-01-01'
+
+# Run analysis
+df, summary = collector.run_analysis(
+    series_ids=custom_series,
+    start_date=start_date,
+    end_date=end_date
+)
+```
+
+## Available Economic Indicators
+
+The tool includes these common economic indicators:
+
+| Series ID | Description |
+|-----------|-------------|
+| GDP | Gross Domestic Product |
+| UNRATE | Unemployment Rate |
+| CPIAUCSL | Consumer Price Index |
+| FEDFUNDS | Federal Funds Rate |
+| DGS10 | 10-Year Treasury Rate |
+| DEXUSEU | US/Euro Exchange Rate |
+| PAYEMS | Total Nonfarm Payrolls |
+| INDPRO | Industrial Production |
+| M2SL | M2 Money Stock |
+| PCE | Personal Consumption Expenditures |
+
+## Output Files
+
+### Data Files
+- CSV files saved in the `data/` directory
+- Timestamped filenames (e.g., `fred_economic_data_20241201_143022.csv`)
+
+### Visualization Files
+- PNG plots saved in the `plots/` directory
+- High-resolution charts with economic indicator time series
+
+## API Rate Limits
+
+The FRED API has rate limits:
+- 120 requests per minute
+- 1000 requests per day
+
+The tool includes error handling for rate limit issues.
+
+## Configuration
+
+Edit `config.py` to customize:
+- API key (if needed)
+- Default date ranges
+- Output directories
+- Default indicators
+
+## Dependencies
+
+- `fredapi`: FRED API client
+- `pandas`: Data manipulation
+- `numpy`: Numerical computing
+- `matplotlib`: Plotting
+- `seaborn`: Statistical visualization
+- `jupyter`: Interactive notebooks (optional)
+
+## Error Handling
+
+The tool includes comprehensive error handling for:
+- API connection issues
+- Invalid series IDs
+- Rate limit exceeded
+- Data format errors
+
+## Contributing
+
+To add new features:
+1. Extend the `FREDDataCollector` class
+2. Add new methods for specific analysis
+3. Update the configuration as needed
+
+## License
+
+This project is for educational and research purposes. Please respect FRED API terms of service.
+
+## Support
+
+For issues with the FRED API, visit: https://fred.stlouisfed.org/docs/api/ 

config/pipeline.yaml

@@ -0,0 +1,16 @@
+fred:
+  api_key: "acf8bbec7efe3b6dfa6ae083e7152314"
+  series:
+    - GDP
+    - UNRATE
+    - CPIAUCSL
+    - FEDFUNDS
+    - DGS10
+  start_date: "2010-01-01"
+  end_date: "2024-01-01"
+  output_dir: "data/processed"
+  export_dir: "data/exports"
+  schedule: "0 6 * * *"  # Every day at 6am UTC
+logging:
+  level: INFO
+  file: logs/pipeline.log 

config/settings.py

@@ -0,0 +1,10 @@
+# FRED API Configuration
+FRED_API_KEY = "acf8bbec7efe3b6dfa6ae083e7152314"
+
+# Data settings
+DEFAULT_START_DATE = "2010-01-01"
+DEFAULT_END_DATE = "2024-01-01"
+
+# Output settings
+OUTPUT_DIR = "data"
+PLOTS_DIR = "plots" 

data/exports/regression_summary.txt

@@ -0,0 +1,28 @@
+                            OLS Regression Results                            
+==============================================================================
+Dep. Variable:                    GDP   R-squared:                       0.971
+Model:                            OLS   Adj. R-squared:                  0.970
+Method:                 Least Squares   F-statistic:                     839.9
+Date:                Thu, 10 Jul 2025   Prob (F-statistic):           5.55e-76
+Time:                        22:30:42   Log-Likelihood:                -903.30
+No. Observations:                 105   AIC:                             1817.
+Df Residuals:                     100   BIC:                             1830.
+Df Model:                           4                                         
+Covariance Type:            nonrobust                                         
+==============================================================================
+                 coef    std err          t      P>|t|      [0.025      0.975]
+------------------------------------------------------------------------------
+const       -328.8855    630.799     -0.521      0.603   -1580.374     922.603
+UNRATE       -21.7142     79.789     -0.272      0.786    -180.013     136.584
+CPIAUCSL      85.7935      2.036     42.144      0.000      81.755      89.832
+FEDFUNDS     492.3433     92.591      5.317      0.000     308.646     676.041
+DGS10       -883.8622    122.881     -7.193      0.000   -1127.655    -640.070
+==============================================================================
+Omnibus:                       12.409   Durbin-Watson:                   2.138
+Prob(Omnibus):                  0.002   Jarque-Bera (JB):               13.297
+Skew:                           0.746   Prob(JB):                      0.00130
+Kurtosis:                       3.902   Cond. No.                         812.
+==============================================================================
+
+Notes:
+[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

requirements.txt

@@ -0,0 +1,13 @@
+fredapi==0.4.2
+pandas==2.1.4
+numpy==1.24.3
+matplotlib==3.7.2
+seaborn==0.12.2
+jupyter==1.0.0
+python-dotenv==1.0.0
+requests==2.31.0
+PyYAML==6.0.2
+APScheduler==3.10.4
+scikit-learn==1.3.0
+scipy==1.11.1
+statsmodels==0.14.0 

scripts/run_advanced_analytics.py

@@ -0,0 +1,56 @@
+#!/usr/bin/env python
+"""
+Advanced Analytics Runner for FRED Economic Data
+Runs comprehensive statistical analysis, modeling, and insights extraction.
+"""
+
+import os
+import sys
+import glob
+sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'src'))
+
+from analysis.advanced_analytics import AdvancedAnalytics
+
+def find_latest_data():
+    """Find the most recent FRED data file."""
+    data_files = glob.glob('data/processed/fred_data_*.csv')
+    if not data_files:
+        raise FileNotFoundError("No FRED data files found. Run the pipeline first.")
+    
+    # Get the most recent file
+    latest_file = max(data_files, key=os.path.getctime)
+    print(f"Using data file: {latest_file}")
+    return latest_file
+
+def main():
+    """Run the complete advanced analytics workflow."""
+    print("=" * 80)
+    print("FRED ECONOMIC DATA - ADVANCED ANALYTICS")
+    print("=" * 80)
+    
+    try:
+        # Find the latest data file
+        data_file = find_latest_data()
+        
+        # Initialize analytics
+        analytics = AdvancedAnalytics(data_path=data_file)
+        
+        # Run complete analysis
+        results = analytics.run_complete_analysis()
+        
+        print("\n" + "=" * 80)
+        print("ANALYTICS COMPLETE!")
+        print("=" * 80)
+        print("Generated outputs:")
+        print("  📊 data/exports/insights_report.txt - Comprehensive insights")
+        print("  📈 data/exports/clustering_analysis.png - Clustering results")
+        print("  📉 data/exports/time_series_decomposition.png - Time series decomposition")
+        print("  🔮 data/exports/time_series_forecast.png - Time series forecast")
+        print("\nKey findings have been saved to data/exports/insights_report.txt")
+        
+    except Exception as e:
+        print(f"Error running analytics: {e}")
+        sys.exit(1)
+
+if __name__ == "__main__":
+    main() 

scripts/run_eda.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+"""
+Run EDA: Distributions, skewness, kurtosis, correlations, PCA/t-SNE
+"""
+import os
+import sys
+import glob
+sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'src'))
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+
+# Find latest processed data file
+def find_latest_data():
+    data_files = glob.glob('data/processed/fred_data_*.csv')
+    if not data_files:
+        raise FileNotFoundError("No FRED data files found. Run the pipeline first.")
+    return max(data_files, key=os.path.getctime)
+
+def main():
+    print("="*60)
+    print("FRED EDA: Distributions, Skewness, Kurtosis, Correlations, PCA")
+    print("="*60)
+    data_file = find_latest_data()
+    print(f"Using data file: {data_file}")
+    df = pd.read_csv(data_file, index_col=0, parse_dates=True)
+    df_clean = df.dropna()
+    # 1. Distributions, Skewness, Kurtosis
+    desc = df.describe()
+    skew = df.skew()
+    kurt = df.kurtosis()
+    print("\nDescriptive Statistics:\n", desc)
+    print("\nSkewness:")
+    print(skew)
+    print("\nKurtosis:")
+    print(kurt)
+    # Plot distributions
+    for col in df.columns:
+        plt.figure(figsize=(8,4))
+        sns.histplot(df[col].dropna(), kde=True)
+        plt.title(f"Distribution of {col}")
+        plt.savefig(f"data/exports/distribution_{col}.png", dpi=200, bbox_inches='tight')
+        plt.close()
+    # 2. Correlation matrices
+    pearson_corr = df.corr(method='pearson')
+    spearman_corr = df.corr(method='spearman')
+    print("\nPearson Correlation Matrix:\n", pearson_corr.round(3))
+    print("\nSpearman Correlation Matrix:\n", spearman_corr.round(3))
+    plt.figure(figsize=(8,6))
+    sns.heatmap(pearson_corr, annot=True, cmap='coolwarm', center=0)
+    plt.title('Pearson Correlation Matrix')
+    plt.tight_layout()
+    plt.savefig('data/exports/pearson_corr_matrix.png', dpi=200)
+    plt.close()
+    plt.figure(figsize=(8,6))
+    sns.heatmap(spearman_corr, annot=True, cmap='coolwarm', center=0)
+    plt.title('Spearman Correlation Matrix')
+    plt.tight_layout()
+    plt.savefig('data/exports/spearman_corr_matrix.png', dpi=200)
+    plt.close()
+    # 3. PCA for visualization
+    scaler = StandardScaler()
+    scaled = scaler.fit_transform(df_clean)
+    pca = PCA(n_components=2)
+    pca_result = pca.fit_transform(scaled)
+    pca_df = pd.DataFrame(pca_result, columns=['PC1', 'PC2'], index=df_clean.index)
+    plt.figure(figsize=(8,6))
+    plt.scatter(pca_df['PC1'], pca_df['PC2'], alpha=0.5)
+    plt.xlabel('PC1')
+    plt.ylabel('PC2')
+    plt.title('PCA Projection (2D)')
+    plt.tight_layout()
+    plt.savefig('data/exports/pca_2d.png', dpi=200)
+    plt.close()
+    print("\nEDA complete. Outputs saved to data/exports/.")
+
+if __name__ == "__main__":
+    main() 

scripts/run_fred_pipeline.py

@@ -0,0 +1,10 @@
+#!/usr/bin/env python
+import os
+import sys
+sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'src'))
+from core.fred_pipeline import FREDPipeline
+
+if __name__ == "__main__":
+    config_path = os.path.join(os.path.dirname(__file__), '..', 'config', 'pipeline.yaml')
+    pipeline = FREDPipeline(config_path)
+    pipeline.run() 

scripts/run_segmentation.py

@@ -0,0 +1,91 @@
+#!/usr/bin/env python
+"""
+Run Segmentation: K-means clustering, elbow method, silhouette score, PCA visualization
+"""
+import os
+import sys
+import glob
+sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'src'))
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.cluster import KMeans
+from sklearn.metrics import silhouette_score
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+
+def find_latest_data():
+    data_files = glob.glob('data/processed/fred_data_*.csv')
+    if not data_files:
+        raise FileNotFoundError("No FRED data files found. Run the pipeline first.")
+    return max(data_files, key=os.path.getctime)
+
+def main():
+    print("="*60)
+    print("FRED Segmentation: K-means, Elbow, Silhouette, PCA Visualization")
+    print("="*60)
+    data_file = find_latest_data()
+    print(f"Using data file: {data_file}")
+    df = pd.read_csv(data_file, index_col=0, parse_dates=True)
+    df_clean = df.dropna()
+    if df_clean.shape[0] < 10 or df_clean.shape[1] < 2:
+        print("Not enough data for clustering (need at least 10 rows and 2 columns after dropna). Skipping.")
+        return
+    scaler = StandardScaler()
+    scaled_data = scaler.fit_transform(df_clean)
+    # Elbow and silhouette
+    inertias = []
+    silhouette_scores = []
+    k_range = range(2, min(11, len(df_clean)//10+1))
+    for k in k_range:
+        kmeans = KMeans(n_clusters=k, random_state=42)
+        kmeans.fit(scaled_data)
+        inertias.append(kmeans.inertia_)
+        silhouette_scores.append(silhouette_score(scaled_data, kmeans.labels_))
+    # Plot elbow and silhouette
+    plt.figure(figsize=(12,4))
+    plt.subplot(1,2,1)
+    plt.plot(list(k_range), inertias, 'bo-')
+    plt.xlabel('Number of Clusters (k)')
+    plt.ylabel('Inertia')
+    plt.title('Elbow Method')
+    plt.grid(True)
+    plt.subplot(1,2,2)
+    plt.plot(list(k_range), silhouette_scores, 'ro-')
+    plt.xlabel('Number of Clusters (k)')
+    plt.ylabel('Silhouette Score')
+    plt.title('Silhouette Analysis')
+    plt.grid(True)
+    plt.tight_layout()
+    plt.savefig('data/exports/clustering_analysis.png', dpi=200)
+    plt.close()
+    # Choose optimal k
+    optimal_k = list(k_range)[np.argmax(silhouette_scores)]
+    print(f"Optimal number of clusters: {optimal_k}")
+    print(f"Best silhouette score: {max(silhouette_scores):.3f}")
+    # Final clustering
+    kmeans_optimal = KMeans(n_clusters=optimal_k, random_state=42)
+    cluster_labels = kmeans_optimal.fit_predict(scaled_data)
+    df_clustered = df_clean.copy()
+    df_clustered['Cluster'] = cluster_labels
+    # Cluster stats
+    cluster_stats = df_clustered.groupby('Cluster').agg(['mean', 'std'])
+    print("\nCluster Characteristics:")
+    print(cluster_stats.round(3))
+    # PCA visualization
+    pca = PCA(n_components=2)
+    pca_result = pca.fit_transform(scaled_data)
+    plt.figure(figsize=(8,6))
+    scatter = plt.scatter(pca_result[:,0], pca_result[:,1], c=cluster_labels, cmap='tab10', alpha=0.7)
+    plt.xlabel('PC1')
+    plt.ylabel('PC2')
+    plt.title('Clusters Visualized with PCA')
+    plt.legend(*scatter.legend_elements(), title="Cluster")
+    plt.tight_layout()
+    plt.savefig('data/exports/clusters_pca.png', dpi=200)
+    plt.close()
+    print("\nSegmentation complete. Outputs saved to data/exports/.")
+
+if __name__ == "__main__":
+    main() 

scripts/run_statistical_modeling.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python
+"""
+Run Statistical Modeling: Linear regression, diagnostics, p-values, confidence intervals, plots
+"""
+import os
+import sys
+import glob
+sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'src'))
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+import statsmodels.api as sm
+from scipy import stats
+from statsmodels.stats.diagnostic import het_breuschpagan
+from statsmodels.stats.outliers_influence import variance_inflation_factor
+
+def find_latest_data():
+    data_files = glob.glob('data/processed/fred_data_*.csv')
+    if not data_files:
+        raise FileNotFoundError("No FRED data files found. Run the pipeline first.")
+    return max(data_files, key=os.path.getctime)
+
+def main():
+    print("="*60)
+    print("FRED Statistical Modeling: Linear Regression & Diagnostics")
+    print("="*60)
+    data_file = find_latest_data()
+    print(f"Using data file: {data_file}")
+    df = pd.read_csv(data_file, index_col=0, parse_dates=True)
+    df_clean = df.dropna()
+    target_var = 'GDP'
+    if target_var not in df_clean.columns:
+        print(f"Target variable '{target_var}' not found in data.")
+        return
+    feature_cols = [col for col in df_clean.columns if col != target_var]
+    X = df_clean[feature_cols]
+    y = df_clean[target_var]
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    # Fit linear regression
+    model = LinearRegression()
+    model.fit(X_train, y_train)
+    y_pred_train = model.predict(X_train)
+    y_pred_test = model.predict(X_test)
+    # Model performance
+    r2_train = model.score(X_train, y_train)
+    r2_test = model.score(X_test, y_test)
+    print(f"R² (Train): {r2_train:.4f} | R² (Test): {r2_test:.4f}")
+    # Coefficients
+    print("\nCoefficients:")
+    for feature, coef in zip(feature_cols, model.coef_):
+        print(f"  {feature}: {coef:.4f}")
+    print(f"  Intercept: {model.intercept_:.4f}")
+    # Statsmodels for p-values and CIs
+    X_with_const = sm.add_constant(X_train)
+    model_sm = sm.OLS(y_train, X_with_const).fit()
+    print("\nStatistical Significance:")
+    print(model_sm.summary().tables[1])
+    # Save summary table
+    with open('data/exports/regression_summary.txt', 'w') as f:
+        f.write(str(model_sm.summary()))
+    # Residuals
+    residuals = y_train - y_pred_train
+    # Normality test
+    _, p_value_norm = stats.normaltest(residuals)
+    print(f"Normality test (p-value): {p_value_norm:.4f}")
+    # VIF
+    vif_data = []
+    for i in range(X_train.shape[1]):
+        try:
+            vif = variance_inflation_factor(X_train.values, i)
+            vif_data.append(vif)
+        except:
+            vif_data.append(np.nan)
+    print("\nVariance Inflation Factors:")
+    for feature, vif in zip(feature_cols, vif_data):
+        print(f"  {feature}: {vif:.3f}")
+    # Homoscedasticity
+    try:
+        _, p_value_het = het_breuschpagan(residuals, X_with_const)
+        print(f"Homoscedasticity test (p-value): {p_value_het:.4f}")
+    except:
+        print("Homoscedasticity test failed")
+    # Diagnostic plots
+    plt.figure(figsize=(12,4))
+    plt.subplot(1,2,1)
+    plt.scatter(y_pred_train, residuals, alpha=0.5)
+    plt.axhline(0, color='red', linestyle='--')
+    plt.xlabel('Fitted Values')
+    plt.ylabel('Residuals')
+    plt.title('Residuals vs Fitted')
+    plt.subplot(1,2,2)
+    stats.probplot(residuals, dist="norm", plot=plt)
+    plt.title('Normal Q-Q')
+    plt.tight_layout()
+    plt.savefig('data/exports/regression_diagnostics.png', dpi=200)
+    plt.close()
+    print("\nStatistical modeling complete. Outputs saved to data/exports/.")
+
+if __name__ == "__main__":
+    main() 

scripts/run_time_series.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+"""
+Run Time Series Analysis: Decomposition, ARIMA forecasting, plots
+"""
+import os
+import sys
+import glob
+sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'src'))
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from statsmodels.tsa.seasonal import seasonal_decompose
+from statsmodels.tsa.arima.model import ARIMA
+
+def find_latest_data():
+    data_files = glob.glob('data/processed/fred_data_*.csv')
+    if not data_files:
+        raise FileNotFoundError("No FRED data files found. Run the pipeline first.")
+    return max(data_files, key=os.path.getctime)
+
+def main():
+    print("="*60)
+    print("FRED Time Series Analysis: Decomposition & ARIMA Forecasting")
+    print("="*60)
+    data_file = find_latest_data()
+    print(f"Using data file: {data_file}")
+    df = pd.read_csv(data_file, index_col=0, parse_dates=True)
+    target_var = 'GDP'
+    if target_var not in df.columns:
+        print(f"Target variable '{target_var}' not found in data.")
+        return
+    ts_data = df[target_var].dropna()
+    if len(ts_data) < 50:
+        print("Insufficient data for time series analysis (need at least 50 points). Skipping.")
+        return
+    print(f"Time series length: {len(ts_data)} observations")
+    print(f"Date range: {ts_data.index.min()} to {ts_data.index.max()}")
+    # Decomposition
+    try:
+        if ts_data.index.freq is None:
+            ts_monthly = ts_data.resample('M').mean()
+        else:
+            ts_monthly = ts_data
+        decomposition = seasonal_decompose(ts_monthly, model='additive', period=12)
+        fig, axes = plt.subplots(4, 1, figsize=(12, 10))
+        decomposition.observed.plot(ax=axes[0], title='Original Time Series')
+        decomposition.trend.plot(ax=axes[1], title='Trend')
+        decomposition.seasonal.plot(ax=axes[2], title='Seasonality')
+        decomposition.resid.plot(ax=axes[3], title='Residuals')
+        plt.tight_layout()
+        plt.savefig('data/exports/time_series_decomposition.png', dpi=200, bbox_inches='tight')
+        plt.close()
+        print("Decomposition plot saved.")
+    except Exception as e:
+        print(f"Decomposition failed: {e}")
+    # ARIMA Forecasting
+    try:
+        model = ARIMA(ts_monthly, order=(1, 1, 1))
+        fitted_model = model.fit()
+        print(f"ARIMA Model Summary:\n{fitted_model.summary()}")
+        forecast_steps = min(12, len(ts_monthly) // 4)
+        forecast = fitted_model.forecast(steps=forecast_steps)
+        conf_int = fitted_model.get_forecast(steps=forecast_steps).conf_int()
+        plt.figure(figsize=(12, 6))
+        ts_monthly.plot(label='Historical Data')
+        forecast.plot(label='Forecast', color='red')
+        plt.fill_between(forecast.index, conf_int.iloc[:, 0], conf_int.iloc[:, 1], alpha=0.3, color='red', label='Confidence Interval')
+        plt.title(f'{target_var} - ARIMA Forecast')
+        plt.legend()
+        plt.grid(True)
+        plt.tight_layout()
+        plt.savefig('data/exports/time_series_forecast.png', dpi=200, bbox_inches='tight')
+        plt.close()
+        print("Forecast plot saved.")
+    except Exception as e:
+        print(f"ARIMA modeling failed: {e}")
+    print("\nTime series analysis complete. Outputs saved to data/exports/.")
+
+if __name__ == "__main__":
+    main() 

src/__init__.py

@@ -0,0 +1,21 @@
+"""
+FRED Economic Data Analysis Package
+
+A comprehensive tool for collecting, analyzing, and visualizing 
+Federal Reserve Economic Data (FRED) using the FRED API.
+
+Author: Economic Data Team
+Version: 1.0.0
+"""
+
+__version__ = "1.0.0"
+__author__ = "Economic Data Team"
+__email__ = "data-team@company.com"
+
+from .core.fred_client import FREDDataCollectorV2
+from .analysis.advanced_analytics import AdvancedAnalytics
+
+__all__ = [
+    'FREDDataCollectorV2',
+    'AdvancedAnalytics',
+] 

src/analysis/__init__.py

@@ -0,0 +1,7 @@
+"""
+Economic data analysis and visualization tools.
+"""
+
+from .advanced_analytics import AdvancedAnalytics
+
+__all__ = ['AdvancedAnalytics'] 

src/analysis/advanced_analytics.py

@@ -0,0 +1,517 @@
+#!/usr/bin/env python3
+"""
+Advanced Analytics Module for FRED Economic Data
+Performs comprehensive statistical analysis, modeling, and insights extraction.
+"""
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from scipy import stats
+from sklearn.preprocessing import StandardScaler
+from sklearn.decomposition import PCA
+from sklearn.cluster import KMeans
+from sklearn.metrics import silhouette_score
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import r2_score, mean_squared_error
+import statsmodels.api as sm
+from statsmodels.tsa.seasonal import seasonal_decompose
+from statsmodels.tsa.arima.model import ARIMA
+from statsmodels.stats.diagnostic import het_breuschpagan
+from statsmodels.stats.outliers_influence import variance_inflation_factor
+import warnings
+warnings.filterwarnings('ignore')
+
+class AdvancedAnalytics:
+    """
+    Comprehensive analytics class for FRED economic data.
+    Performs EDA, statistical modeling, segmentation, and time series analysis.
+    """
+    
+    def __init__(self, data_path=None, df=None):
+        """Initialize with data path or DataFrame."""
+        if df is not None:
+            self.df = df
+        elif data_path:
+            self.df = pd.read_csv(data_path, index_col=0, parse_dates=True)
+        else:
+            raise ValueError("Must provide either data_path or DataFrame")
+        
+        self.scaler = StandardScaler()
+        self.results = {}
+        
+    def perform_eda(self):
+        """Perform comprehensive Exploratory Data Analysis."""
+        print("=" * 60)
+        print("EXPLORATORY DATA ANALYSIS")
+        print("=" * 60)
+        
+        # Basic info
+        print(f"\nDataset Shape: {self.df.shape}")
+        print(f"Date Range: {self.df.index.min()} to {self.df.index.max()}")
+        print(f"Variables: {list(self.df.columns)}")
+        
+        # Descriptive statistics
+        print("\n" + "=" * 40)
+        print("DESCRIPTIVE STATISTICS")
+        print("=" * 40)
+        desc_stats = self.df.describe()
+        print(desc_stats)
+        
+        # Skewness and Kurtosis
+        print("\n" + "=" * 40)
+        print("SKEWNESS AND KURTOSIS")
+        print("=" * 40)
+        skewness = self.df.skew()
+        kurtosis = self.df.kurtosis()
+        
+        for col in self.df.columns:
+            print(f"{col}:")
+            print(f"  Skewness: {skewness[col]:.3f}")
+            print(f"  Kurtosis: {kurtosis[col]:.3f}")
+        
+        # Correlation Analysis
+        print("\n" + "=" * 40)
+        print("CORRELATION ANALYSIS")
+        print("=" * 40)
+        
+        # Pearson correlation
+        pearson_corr = self.df.corr(method='pearson')
+        print("\nPearson Correlation Matrix:")
+        print(pearson_corr.round(3))
+        
+        # Spearman correlation
+        spearman_corr = self.df.corr(method='spearman')
+        print("\nSpearman Correlation Matrix:")
+        print(spearman_corr.round(3))
+        
+        # Store results
+        self.results['eda'] = {
+            'descriptive_stats': desc_stats,
+            'skewness': skewness,
+            'kurtosis': kurtosis,
+            'pearson_corr': pearson_corr,
+            'spearman_corr': spearman_corr
+        }
+        
+        return self.results['eda']
+    
+    def perform_dimensionality_reduction(self, method='pca', n_components=2):
+        """Perform dimensionality reduction for visualization."""
+        print("\n" + "=" * 40)
+        print(f"DIMENSIONALITY REDUCTION ({method.upper()})")
+        print("=" * 40)
+        
+        # Prepare data (remove NaN values)
+        df_clean = self.df.dropna()
+        
+        if method.lower() == 'pca':
+            # PCA
+            pca = PCA(n_components=n_components)
+            scaled_data = self.scaler.fit_transform(df_clean)
+            pca_result = pca.fit_transform(scaled_data)
+            
+            print(f"Explained variance ratio: {pca.explained_variance_ratio_}")
+            print(f"Total explained variance: {sum(pca.explained_variance_ratio_):.3f}")
+            
+            # Create DataFrame with PCA results
+            pca_df = pd.DataFrame(
+                pca_result, 
+                columns=[f'PC{i+1}' for i in range(n_components)],
+                index=df_clean.index
+            )
+            
+            self.results['pca'] = {
+                'components': pca_df,
+                'explained_variance': pca.explained_variance_ratio_,
+                'feature_importance': pd.DataFrame(
+                    pca.components_.T,
+                    columns=[f'PC{i+1}' for i in range(n_components)],
+                    index=df_clean.columns
+                )
+            }
+            
+            return self.results['pca']
+        
+        return None
+    
+    def perform_statistical_modeling(self, target_var='GDP', test_size=0.2):
+        """Perform linear regression with comprehensive diagnostics."""
+        print("\n" + "=" * 40)
+        print("STATISTICAL MODELING - LINEAR REGRESSION")
+        print("=" * 40)
+        
+        # Prepare data
+        df_clean = self.df.dropna()
+        
+        if target_var not in df_clean.columns:
+            print(f"Target variable '{target_var}' not found in dataset")
+            return None
+        
+        # Prepare features and target
+        feature_cols = [col for col in df_clean.columns if col != target_var]
+        X = df_clean[feature_cols]
+        y = df_clean[target_var]
+        
+        # Split data
+        X_train, X_test, y_train, y_test = train_test_split(
+            X, y, test_size=test_size, random_state=42
+        )
+        
+        # Fit linear regression
+        model = LinearRegression()
+        model.fit(X_train, y_train)
+        
+        # Predictions
+        y_pred_train = model.predict(X_train)
+        y_pred_test = model.predict(X_test)
+        
+        # Model performance
+        r2_train = r2_score(y_train, y_pred_train)
+        r2_test = r2_score(y_test, y_pred_test)
+        rmse_train = np.sqrt(mean_squared_error(y_train, y_pred_train))
+        rmse_test = np.sqrt(mean_squared_error(y_test, y_pred_test))
+        
+        print(f"\nModel Performance:")
+        print(f"R² (Training): {r2_train:.4f}")
+        print(f"R² (Test): {r2_test:.4f}")
+        print(f"RMSE (Training): {rmse_train:.4f}")
+        print(f"RMSE (Test): {rmse_test:.4f}")
+        
+        # Coefficients
+        print(f"\nCoefficients:")
+        for feature, coef in zip(feature_cols, model.coef_):
+            print(f"  {feature}: {coef:.4f}")
+        print(f"  Intercept: {model.intercept_:.4f}")
+        
+        # Statistical significance using statsmodels
+        X_with_const = sm.add_constant(X_train)
+        model_sm = sm.OLS(y_train, X_with_const).fit()
+        
+        print(f"\nStatistical Significance:")
+        print(model_sm.summary().tables[1])
+        
+        # Assumption tests
+        print(f"\n" + "=" * 30)
+        print("REGRESSION ASSUMPTIONS")
+        print("=" * 30)
+        
+        # 1. Normality of residuals
+        residuals = y_train - y_pred_train
+        _, p_value_norm = stats.normaltest(residuals)
+        print(f"Normality test (p-value): {p_value_norm:.4f}")
+        
+        # 2. Multicollinearity (VIF)
+        vif_data = []
+        for i in range(X_train.shape[1]):
+            try:
+                vif = variance_inflation_factor(X_train.values, i)
+                vif_data.append(vif)
+            except:
+                vif_data.append(np.nan)
+        
+        print(f"\nVariance Inflation Factors:")
+        for feature, vif in zip(feature_cols, vif_data):
+            print(f"  {feature}: {vif:.3f}")
+        
+        # 3. Homoscedasticity
+        try:
+            _, p_value_het = het_breuschpagan(residuals, X_with_const)
+            print(f"\nHomoscedasticity test (p-value): {p_value_het:.4f}")
+        except:
+            p_value_het = np.nan
+            print(f"\nHomoscedasticity test failed")
+        
+        # Store results
+        self.results['regression'] = {
+            'model': model,
+            'model_sm': model_sm,
+            'performance': {
+                'r2_train': r2_train,
+                'r2_test': r2_test,
+                'rmse_train': rmse_train,
+                'rmse_test': rmse_test
+            },
+            'coefficients': dict(zip(feature_cols, model.coef_)),
+            'assumptions': {
+                'normality_p': p_value_norm,
+                'homoscedasticity_p': p_value_het,
+                'vif': dict(zip(feature_cols, vif_data))
+            }
+        }
+        
+        return self.results['regression']
+    
+    def perform_clustering(self, max_k=10):
+        """Perform clustering analysis with optimal k selection."""
+        print("\n" + "=" * 40)
+        print("CLUSTERING ANALYSIS")
+        print("=" * 40)
+        
+        # Prepare data
+        df_clean = self.df.dropna()
+        if df_clean.shape[0] < 10 or df_clean.shape[1] < 2:
+            print("Not enough data for clustering (need at least 10 rows and 2 columns after dropna). Skipping.")
+            self.results['clustering'] = None
+            return None
+        try:
+            scaled_data = self.scaler.fit_transform(df_clean)
+        except Exception as e:
+            print(f"Scaling failed: {e}")
+            self.results['clustering'] = None
+            return None
+        # Find optimal k using elbow method and silhouette score
+        inertias = []
+        silhouette_scores = []
+        k_range = range(2, min(max_k + 1, len(df_clean) // 10 + 1))
+        if len(k_range) < 2:
+            print("Not enough data for multiple clusters. Skipping clustering.")
+            self.results['clustering'] = None
+            return None
+        try:
+            for k in k_range:
+                kmeans = KMeans(n_clusters=k, random_state=42)
+                kmeans.fit(scaled_data)
+                inertias.append(kmeans.inertia_)
+                silhouette_scores.append(silhouette_score(scaled_data, kmeans.labels_))
+            # Plot elbow curve only if there are results
+            if inertias and silhouette_scores:
+                plt.figure(figsize=(12, 4))
+                plt.subplot(1, 2, 1)
+                plt.plot(list(k_range), inertias, 'bo-')
+                plt.xlabel('Number of Clusters (k)')
+                plt.ylabel('Inertia')
+                plt.title('Elbow Method')
+                plt.grid(True)
+                plt.subplot(1, 2, 2)
+                plt.plot(list(k_range), silhouette_scores, 'ro-')
+                plt.xlabel('Number of Clusters (k)')
+                plt.ylabel('Silhouette Score')
+                plt.title('Silhouette Analysis')
+                plt.grid(True)
+                plt.tight_layout()
+                plt.savefig('data/exports/clustering_analysis.png', dpi=300, bbox_inches='tight')
+                plt.show()
+            # Choose optimal k (highest silhouette score)
+            optimal_k = list(k_range)[np.argmax(silhouette_scores)]
+            print(f"Optimal number of clusters: {optimal_k}")
+            print(f"Best silhouette score: {max(silhouette_scores):.3f}")
+            # Perform clustering with optimal k
+            kmeans_optimal = KMeans(n_clusters=optimal_k, random_state=42)
+            cluster_labels = kmeans_optimal.fit_predict(scaled_data)
+            # Add cluster labels to data
+            df_clustered = df_clean.copy()
+            df_clustered['Cluster'] = cluster_labels
+            # Cluster characteristics
+            print(f"\nCluster Characteristics:")
+            cluster_stats = df_clustered.groupby('Cluster').agg(['mean', 'std'])
+            print(cluster_stats.round(3))
+            # Store results
+            self.results['clustering'] = {
+                'optimal_k': optimal_k,
+                'silhouette_score': max(silhouette_scores),
+                'cluster_labels': cluster_labels,
+                'clustered_data': df_clustered,
+                'cluster_stats': cluster_stats,
+                'inertias': inertias,
+                'silhouette_scores': silhouette_scores
+            }
+            return self.results['clustering']
+        except Exception as e:
+            print(f"Clustering failed: {e}")
+            self.results['clustering'] = None
+            return None
+    
+    def perform_time_series_analysis(self, target_var='GDP'):
+        """Perform comprehensive time series analysis."""
+        print("\n" + "=" * 40)
+        print("TIME SERIES ANALYSIS")
+        print("=" * 40)
+        
+        if target_var not in self.df.columns:
+            print(f"Target variable '{target_var}' not found")
+            self.results['time_series'] = None
+            return None
+        # Prepare time series data
+        ts_data = self.df[target_var].dropna()
+        if len(ts_data) < 50:
+            print("Insufficient data for time series analysis (need at least 50 points). Skipping.")
+            self.results['time_series'] = None
+            return None
+        print(f"Time series length: {len(ts_data)} observations")
+        print(f"Date range: {ts_data.index.min()} to {ts_data.index.max()}")
+        # 1. Time Series Decomposition
+        print(f"\nTime Series Decomposition:")
+        try:
+            # Resample to monthly data if needed
+            if ts_data.index.freq is None:
+                ts_monthly = ts_data.resample('M').mean()
+            else:
+                ts_monthly = ts_data
+            decomposition = seasonal_decompose(ts_monthly, model='additive', period=12)
+            # Plot decomposition
+            fig, axes = plt.subplots(4, 1, figsize=(12, 10))
+            decomposition.observed.plot(ax=axes[0], title='Original Time Series')
+            decomposition.trend.plot(ax=axes[1], title='Trend')
+            decomposition.seasonal.plot(ax=axes[2], title='Seasonality')
+            decomposition.resid.plot(ax=axes[3], title='Residuals')
+            plt.tight_layout()
+            plt.savefig('data/exports/time_series_decomposition.png', dpi=300, bbox_inches='tight')
+            plt.show()
+        except Exception as e:
+            print(f"Decomposition failed: {e}")
+        # 2. ARIMA Modeling
+        print(f"\nARIMA Modeling:")
+        try:
+            # Fit ARIMA model
+            model = ARIMA(ts_monthly, order=(1, 1, 1))
+            fitted_model = model.fit()
+            print(f"ARIMA Model Summary:")
+            print(fitted_model.summary())
+            # Forecast
+            forecast_steps = min(12, len(ts_monthly) // 4)
+            forecast = fitted_model.forecast(steps=forecast_steps)
+            conf_int = fitted_model.get_forecast(steps=forecast_steps).conf_int()
+            # Plot forecast
+            plt.figure(figsize=(12, 6))
+            ts_monthly.plot(label='Historical Data')
+            forecast.plot(label='Forecast', color='red')
+            plt.fill_between(forecast.index, 
+                           conf_int.iloc[:, 0], 
+                           conf_int.iloc[:, 1], 
+                           alpha=0.3, color='red', label='Confidence Interval')
+            plt.title(f'{target_var} - ARIMA Forecast')
+            plt.legend()
+            plt.grid(True)
+            plt.tight_layout()
+            plt.savefig('data/exports/time_series_forecast.png', dpi=300, bbox_inches='tight')
+            plt.show()
+            # Store results
+            self.results['time_series'] = {
+                'model': fitted_model,
+                'forecast': forecast,
+                'confidence_intervals': conf_int,
+                'decomposition': decomposition if 'decomposition' in locals() else None
+            }
+        except Exception as e:
+            print(f"ARIMA modeling failed: {e}")
+            self.results['time_series'] = None
+        return self.results.get('time_series')
+    
+    def generate_insights_report(self):
+        """Generate comprehensive insights report in layman's terms."""
+        print("\n" + "=" * 60)
+        print("COMPREHENSIVE INSIGHTS REPORT")
+        print("=" * 60)
+        
+        insights = []
+        # EDA Insights
+        if 'eda' in self.results and self.results['eda'] is not None:
+            insights.append("EXPLORATORY DATA ANALYSIS INSIGHTS:")
+            insights.append("-" * 40)
+            # Correlation insights
+            pearson_corr = self.results['eda']['pearson_corr']
+            high_corr_pairs = []
+            for i in range(len(pearson_corr.columns)):
+                for j in range(i+1, len(pearson_corr.columns)):
+                    corr_val = pearson_corr.iloc[i, j]
+                    if abs(corr_val) > 0.7:
+                        high_corr_pairs.append((pearson_corr.columns[i], pearson_corr.columns[j], corr_val))
+            if high_corr_pairs:
+                insights.append("Strong correlations found:")
+                for var1, var2, corr in high_corr_pairs:
+                    insights.append(f"  • {var1} and {var2}: {corr:.3f}")
+            else:
+                insights.append("No strong correlations (>0.7) found between variables.")
+        else:
+            insights.append("EDA could not be performed or returned no results.")
+        # Regression Insights
+        if 'regression' in self.results and self.results['regression'] is not None:
+            insights.append("\nREGRESSION MODEL INSIGHTS:")
+            insights.append("-" * 40)
+            reg_results = self.results['regression']
+            r2_test = reg_results['performance']['r2_test']
+            insights.append(f"Model Performance:")
+            insights.append(f"  • The model explains {r2_test:.1%} of the variation in the target variable")
+            if r2_test > 0.7:
+                insights.append("  • This is considered a good model fit")
+            elif r2_test > 0.5:
+                insights.append("  • This is considered a moderate model fit")
+            else:
+                insights.append("  • This model has limited predictive power")
+            # Assumption insights
+            assumptions = reg_results['assumptions']
+            if assumptions['normality_p'] > 0.05:
+                insights.append("  • Residuals are normally distributed (assumption met)")
+            else:
+                insights.append("  • Residuals are not normally distributed (assumption violated)")
+        else:
+            insights.append("Regression modeling could not be performed or returned no results.")
+        # Clustering Insights
+        if 'clustering' in self.results and self.results['clustering'] is not None:
+            insights.append("\nCLUSTERING INSIGHTS:")
+            insights.append("-" * 40)
+            cluster_results = self.results['clustering']
+            optimal_k = cluster_results['optimal_k']
+            silhouette_score = cluster_results['silhouette_score']
+            insights.append(f"Optimal number of clusters: {optimal_k}")
+            insights.append(f"Cluster quality score: {silhouette_score:.3f}")
+            if silhouette_score > 0.5:
+                insights.append("  • Clusters are well-separated and distinct")
+            elif silhouette_score > 0.3:
+                insights.append("  • Clusters show moderate separation")
+            else:
+                insights.append("  • Clusters may not be well-defined")
+        else:
+            insights.append("Clustering could not be performed or returned no results.")
+        # Time Series Insights
+        if 'time_series' in self.results and self.results['time_series'] is not None:
+            insights.append("\nTIME SERIES INSIGHTS:")
+            insights.append("-" * 40)
+            insights.append("  • Time series decomposition shows trend, seasonality, and random components")
+            insights.append("  • ARIMA model provides future forecasts with confidence intervals")
+            insights.append("  • Forecasts can be used for planning and decision-making")
+        else:
+            insights.append("Time series analysis could not be performed or returned no results.")
+        # Print insights
+        for insight in insights:
+            print(insight)
+        # Save insights to file
+        with open('data/exports/insights_report.txt', 'w') as f:
+            f.write('\n'.join(insights))
+        return insights
+    
+    def run_complete_analysis(self):
+        """Run the complete advanced analytics workflow."""
+        print("Starting comprehensive advanced analytics...")
+        
+        # 1. EDA
+        self.perform_eda()
+        
+        # 2. Dimensionality reduction
+        self.perform_dimensionality_reduction()
+        
+        # 3. Statistical modeling
+        self.perform_statistical_modeling()
+        
+        # 4. Clustering
+        self.perform_clustering()
+        
+        # 5. Time series analysis
+        self.perform_time_series_analysis()
+        
+        # 6. Generate insights
+        self.generate_insights_report()
+        
+        print("\n" + "=" * 60)
+        print("ANALYSIS COMPLETE!")
+        print("=" * 60)
+        print("Check the following outputs:")
+        print("  • data/exports/insights_report.txt - Comprehensive insights")
+        print("  • data/exports/clustering_analysis.png - Clustering results")
+        print("  • data/exports/time_series_decomposition.png - Time series decomposition")
+        print("  • data/exports/time_series_forecast.png - Time series forecast")
+        
+        return self.results 

src/analysis/economic_analyzer.py

@@ -0,0 +1,201 @@
+#!/usr/bin/env python3
+"""
+Quick Start Guide for FRED Economic Data Analysis
+Demonstrates how to load and analyze the collected data
+"""
+
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+import sys
+import os
+sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
+
+from core.fred_client import FREDDataCollectorV2
+from datetime import datetime, timedelta
+
+def load_latest_data():
+    """Load the most recent data file."""
+    import os
+    import glob
+    
+    # Find the most recent data file
+    data_files = glob.glob('data/fred_economic_data_*.csv')
+    if not data_files:
+        print("No data files found. Run the collector first.")
+        return None
+    
+    latest_file = max(data_files, key=os.path.getctime)
+    print(f"Loading data from: {latest_file}")
+    
+    df = pd.read_csv(latest_file, index_col=0, parse_dates=True)
+    return df
+
+def analyze_gdp_trends(df):
+    """Analyze GDP trends."""
+    print("\n=== GDP Analysis ===")
+    
+    if 'GDP' not in df.columns:
+        print("GDP data not available")
+        return
+    
+    gdp_data = df['GDP'].dropna()
+    
+    print(f"GDP Data Points: {len(gdp_data)}")
+    print(f"Date Range: {gdp_data.index.min()} to {gdp_data.index.max()}")
+    print(f"Latest GDP: ${gdp_data.iloc[-1]:,.2f} billion")
+    print(f"GDP Growth (last 5 years): {((gdp_data.iloc[-1] / gdp_data.iloc[-20]) - 1) * 100:.2f}%")
+    
+    # Plot GDP trend
+    plt.figure(figsize=(12, 6))
+    gdp_data.plot(linewidth=2)
+    plt.title('US GDP Over Time')
+    plt.ylabel('GDP (Billions of Dollars)')
+    plt.grid(True, alpha=0.3)
+    plt.tight_layout()
+    plt.show()
+
+def analyze_unemployment(df):
+    """Analyze unemployment trends."""
+    print("\n=== Unemployment Analysis ===")
+    
+    if 'UNRATE' not in df.columns:
+        print("Unemployment data not available")
+        return
+    
+    unrate_data = df['UNRATE'].dropna()
+    
+    print(f"Unemployment Data Points: {len(unrate_data)}")
+    print(f"Current Unemployment Rate: {unrate_data.iloc[-1]:.1f}%")
+    print(f"Average Unemployment Rate: {unrate_data.mean():.1f}%")
+    print(f"Lowest Rate: {unrate_data.min():.1f}%")
+    print(f"Highest Rate: {unrate_data.max():.1f}%")
+    
+    # Plot unemployment trend
+    plt.figure(figsize=(12, 6))
+    unrate_data.plot(linewidth=2, color='red')
+    plt.title('US Unemployment Rate Over Time')
+    plt.ylabel('Unemployment Rate (%)')
+    plt.grid(True, alpha=0.3)
+    plt.tight_layout()
+    plt.show()
+
+def analyze_inflation(df):
+    """Analyze inflation trends using CPI."""
+    print("\n=== Inflation Analysis (CPI) ===")
+    
+    if 'CPIAUCSL' not in df.columns:
+        print("CPI data not available")
+        return
+    
+    cpi_data = df['CPIAUCSL'].dropna()
+    
+    # Calculate year-over-year inflation
+    cpi_yoy = cpi_data.pct_change(periods=12) * 100
+    
+    print(f"CPI Data Points: {len(cpi_data)}")
+    print(f"Current CPI: {cpi_data.iloc[-1]:.2f}")
+    print(f"Current YoY Inflation: {cpi_yoy.iloc[-1]:.2f}%")
+    print(f"Average YoY Inflation: {cpi_yoy.mean():.2f}%")
+    
+    # Plot inflation trend
+    fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 10))
+    
+    cpi_data.plot(ax=ax1, linewidth=2, color='green')
+    ax1.set_title('Consumer Price Index (CPI)')
+    ax1.set_ylabel('CPI')
+    ax1.grid(True, alpha=0.3)
+    
+    cpi_yoy.plot(ax=ax2, linewidth=2, color='orange')
+    ax2.set_title('Year-over-Year Inflation Rate')
+    ax2.set_ylabel('Inflation Rate (%)')
+    ax2.grid(True, alpha=0.3)
+    
+    plt.tight_layout()
+    plt.show()
+
+def analyze_interest_rates(df):
+    """Analyze interest rate trends."""
+    print("\n=== Interest Rate Analysis ===")
+    
+    rates_data = {}
+    if 'FEDFUNDS' in df.columns:
+        rates_data['Federal Funds Rate'] = df['FEDFUNDS'].dropna()
+    if 'DGS10' in df.columns:
+        rates_data['10-Year Treasury'] = df['DGS10'].dropna()
+    
+    if not rates_data:
+        print("No interest rate data available")
+        return
+    
+    for name, data in rates_data.items():
+        print(f"\n{name}:")
+        print(f"  Current Rate: {data.iloc[-1]:.2f}%")
+        print(f"  Average Rate: {data.mean():.2f}%")
+        print(f"  Range: {data.min():.2f}% - {data.max():.2f}%")
+    
+    # Plot interest rates
+    plt.figure(figsize=(12, 6))
+    for name, data in rates_data.items():
+        data.plot(linewidth=2, label=name)
+    
+    plt.title('Interest Rates Over Time')
+    plt.ylabel('Interest Rate (%)')
+    plt.legend()
+    plt.grid(True, alpha=0.3)
+    plt.tight_layout()
+    plt.show()
+
+def correlation_analysis(df):
+    """Analyze correlations between economic indicators."""
+    print("\n=== Correlation Analysis ===")
+    
+    # Select available indicators
+    available_cols = [col for col in ['GDP', 'UNRATE', 'CPIAUCSL', 'FEDFUNDS', 'DGS10'] 
+                     if col in df.columns]
+    
+    if len(available_cols) < 2:
+        print("Need at least 2 indicators for correlation analysis")
+        return
+    
+    # Calculate correlations
+    corr_data = df[available_cols].corr()
+    
+    print("Correlation Matrix:")
+    print(corr_data.round(3))
+    
+    # Plot correlation heatmap
+    plt.figure(figsize=(8, 6))
+    sns.heatmap(corr_data, annot=True, cmap='coolwarm', center=0, 
+                square=True, linewidths=0.5)
+    plt.title('Economic Indicators Correlation Matrix')
+    plt.tight_layout()
+    plt.show()
+
+def main():
+    """Run the quick start analysis."""
+    print("FRED Economic Data - Quick Start Analysis")
+    print("=" * 50)
+    
+    # Load data
+    df = load_latest_data()
+    if df is None:
+        return
+    
+    print(f"Data loaded successfully!")
+    print(f"Shape: {df.shape}")
+    print(f"Columns: {list(df.columns)}")
+    print(f"Date range: {df.index.min()} to {df.index.max()}")
+    
+    # Run analyses
+    analyze_gdp_trends(df)
+    analyze_unemployment(df)
+    analyze_inflation(df)
+    analyze_interest_rates(df)
+    correlation_analysis(df)
+    
+    print("\n=== Analysis Complete ===")
+    print("Check the generated plots for visual insights!")
+
+if __name__ == "__main__":
+    main() 

src/core/__init__.py

@@ -0,0 +1,7 @@
+"""
+Core functionality for FRED data collection and processing.
+"""
+
+from .fred_client import FREDDataCollectorV2
+
+__all__ = ['FREDDataCollectorV2'] 

src/core/base_pipeline.py

@@ -0,0 +1,38 @@
+import abc
+import logging
+import yaml
+import os
+
+class BasePipeline(abc.ABC):
+    """
+    Abstract base class for all data pipelines.
+    Handles config loading, logging, and pipeline orchestration.
+    """
+    def __init__(self, config_path: str):
+        self.config = self.load_config(config_path)
+        self.logger = self.setup_logger()
+
+    @staticmethod
+    def load_config(config_path: str):
+        with open(config_path, 'r') as f:
+            return yaml.safe_load(f)
+
+    def setup_logger(self):
+        log_cfg = self.config.get('logging', {})
+        log_level = getattr(logging, log_cfg.get('level', 'INFO').upper(), logging.INFO)
+        log_file = log_cfg.get('file', 'pipeline.log')
+        os.makedirs(os.path.dirname(log_file), exist_ok=True)
+        logging.basicConfig(
+            level=log_level,
+            format='%(asctime)s %(levelname)s %(name)s %(message)s',
+            handlers=[
+                logging.FileHandler(log_file),
+                logging.StreamHandler()
+            ]
+        )
+        return logging.getLogger(self.__class__.__name__)
+
+    @abc.abstractmethod
+    def run(self):
+        """Run the pipeline (to be implemented by subclasses)."""
+        pass 

src/core/fred_client.py

@@ -0,0 +1,288 @@
+#!/usr/bin/env python3
+"""
+FRED Data Collector v2
+A tool for collecting and analyzing Federal Reserve Economic Data (FRED)
+using direct API calls instead of the fredapi library
+"""
+
+import os
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+import requests
+from datetime import datetime, timedelta
+import warnings
+warnings.filterwarnings('ignore')
+
+import sys
+import os
+sys.path.append(os.path.join(os.path.dirname(__file__), '..', '..'))
+
+from config.settings import FRED_API_KEY, DEFAULT_START_DATE, DEFAULT_END_DATE, OUTPUT_DIR, PLOTS_DIR
+
+class FREDDataCollectorV2:
+    def __init__(self, api_key=None):
+        """Initialize the FRED data collector with API key."""
+        self.api_key = api_key or FRED_API_KEY
+        self.base_url = "https://api.stlouisfed.org/fred"
+        
+        # Create output directories
+        os.makedirs(OUTPUT_DIR, exist_ok=True)
+        os.makedirs(PLOTS_DIR, exist_ok=True)
+        
+        # Common economic indicators
+        self.indicators = {
+            'GDP': 'GDP',  # Gross Domestic Product
+            'UNRATE': 'UNRATE',  # Unemployment Rate
+            'CPIAUCSL': 'CPIAUCSL',  # Consumer Price Index
+            'FEDFUNDS': 'FEDFUNDS',  # Federal Funds Rate
+            'DGS10': 'DGS10',  # 10-Year Treasury Rate
+            'DEXUSEU': 'DEXUSEU',  # US/Euro Exchange Rate
+            'PAYEMS': 'PAYEMS',  # Total Nonfarm Payrolls
+            'INDPRO': 'INDPRO',  # Industrial Production
+            'M2SL': 'M2SL',  # M2 Money Stock
+            'PCE': 'PCE'  # Personal Consumption Expenditures
+        }
+    
+    def get_series_info(self, series_id):
+        """Get information about a FRED series."""
+        try:
+            url = f"{self.base_url}/series"
+            params = {
+                'series_id': series_id,
+                'api_key': self.api_key,
+                'file_type': 'json'
+            }
+            
+            response = requests.get(url, params=params)
+            
+            if response.status_code == 200:
+                data = response.json()
+                series = data.get('seriess', [])
+                
+                if series:
+                    s = series[0]
+                    return {
+                        'id': s['id'],
+                        'title': s['title'],
+                        'units': s.get('units', ''),
+                        'frequency': s.get('frequency', ''),
+                        'last_updated': s.get('last_updated', ''),
+                        'notes': s.get('notes', '')
+                    }
+            
+            return None
+            
+        except Exception as e:
+            print(f"Error getting info for {series_id}: {e}")
+            return None
+    
+    def get_economic_data(self, series_ids, start_date=None, end_date=None):
+        """Fetch economic data for specified series."""
+        start_date = start_date or DEFAULT_START_DATE
+        end_date = end_date or DEFAULT_END_DATE
+        
+        data = {}
+        
+        for series_id in series_ids:
+            try:
+                print(f"Fetching data for {series_id}...")
+                
+                url = f"{self.base_url}/series/observations"
+                params = {
+                    'series_id': series_id,
+                    'api_key': self.api_key,
+                    'file_type': 'json',
+                    'start_date': start_date,
+                    'end_date': end_date
+                }
+                
+                response = requests.get(url, params=params)
+                
+                if response.status_code == 200:
+                    response_data = response.json()
+                    observations = response_data.get('observations', [])
+                    
+                    if observations:
+                        # Convert to pandas Series
+                        dates = []
+                        values = []
+                        
+                        for obs in observations:
+                            try:
+                                date = pd.to_datetime(obs['date'])
+                                value = float(obs['value']) if obs['value'] != '.' else np.nan
+                                dates.append(date)
+                                values.append(value)
+                            except (ValueError, KeyError):
+                                continue
+                        
+                        if dates and values:
+                            series_data = pd.Series(values, index=dates, name=series_id)
+                            data[series_id] = series_data
+                            print(f"✓ Retrieved {len(series_data)} observations for {series_id}")
+                        else:
+                            print(f"✗ No valid data for {series_id}")
+                    else:
+                        print(f"✗ No observations found for {series_id}")
+                else:
+                    print(f"✗ Error fetching {series_id}: HTTP {response.status_code}")
+                    
+            except Exception as e:
+                print(f"✗ Error fetching {series_id}: {e}")
+        
+        return data
+    
+    def create_dataframe(self, data_dict):
+        """Convert dictionary of series data to a pandas DataFrame."""
+        if not data_dict:
+            return pd.DataFrame()
+        
+        # Find the common date range
+        all_dates = set()
+        for series in data_dict.values():
+            all_dates.update(series.index)
+        
+        # Create a complete date range
+        if all_dates:
+            date_range = pd.date_range(min(all_dates), max(all_dates), freq='D')
+            df = pd.DataFrame(index=date_range)
+            
+            # Add each series
+            for series_id, series_data in data_dict.items():
+                df[series_id] = series_data
+            
+            df.index.name = 'Date'
+            return df
+        
+        return pd.DataFrame()
+    
+    def save_data(self, df, filename):
+        """Save data to CSV file."""
+        if df.empty:
+            print("No data to save")
+            return None
+            
+        filepath = os.path.join(OUTPUT_DIR, filename)
+        df.to_csv(filepath)
+        print(f"Data saved to {filepath}")
+        return filepath
+    
+    def plot_economic_indicators(self, df, indicators_to_plot=None):
+        """Create plots for economic indicators."""
+        if df.empty:
+            print("No data to plot")
+            return
+            
+        if indicators_to_plot is None:
+            indicators_to_plot = [col for col in df.columns if col in df.columns]
+        
+        if not indicators_to_plot:
+            print("No indicators to plot")
+            return
+        
+        # Set up the plotting style
+        plt.style.use('default')
+        sns.set_palette("husl")
+        
+        # Create subplots
+        n_indicators = len(indicators_to_plot)
+        fig, axes = plt.subplots(n_indicators, 1, figsize=(15, 4*n_indicators))
+        
+        if n_indicators == 1:
+            axes = [axes]
+        
+        for i, indicator in enumerate(indicators_to_plot):
+            if indicator in df.columns:
+                ax = axes[i]
+                df[indicator].dropna().plot(ax=ax, linewidth=2)
+                
+                # Get series info for title
+                info = self.get_series_info(indicator)
+                title = f'{indicator} - {info["title"]}' if info else indicator
+                ax.set_title(title)
+                ax.set_ylabel('Value')
+                ax.grid(True, alpha=0.3)
+        
+        plt.tight_layout()
+        plot_path = os.path.join(PLOTS_DIR, 'economic_indicators.png')
+        plt.savefig(plot_path, dpi=300, bbox_inches='tight')
+        plt.show()
+        print(f"Plot saved to {plot_path}")
+    
+    def generate_summary_statistics(self, df):
+        """Generate summary statistics for the economic data."""
+        if df.empty:
+            return pd.DataFrame()
+            
+        summary = df.describe()
+        
+        # Add additional statistics
+        summary.loc['missing_values'] = df.isnull().sum()
+        summary.loc['missing_percentage'] = (df.isnull().sum() / len(df)) * 100
+        
+        return summary
+    
+    def run_analysis(self, series_ids=None, start_date=None, end_date=None):
+        """Run a complete analysis of economic indicators."""
+        if series_ids is None:
+            series_ids = list(self.indicators.values())
+        
+        print("=== FRED Economic Data Analysis v2 ===")
+        print(f"API Key: {self.api_key[:8]}...")
+        print(f"Date Range: {start_date or DEFAULT_START_DATE} to {end_date or DEFAULT_END_DATE}")
+        print(f"Series to analyze: {series_ids}")
+        print("=" * 50)
+        
+        # Fetch data
+        data = self.get_economic_data(series_ids, start_date, end_date)
+        
+        if not data:
+            print("No data retrieved. Please check your API key and series IDs.")
+            return None, None
+        
+        # Create DataFrame
+        df = self.create_dataframe(data)
+        
+        if df.empty:
+            print("No data to analyze")
+            return None, None
+        
+        # Save data
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        self.save_data(df, f'fred_economic_data_{timestamp}.csv')
+        
+        # Generate summary statistics
+        summary = self.generate_summary_statistics(df)
+        print("\n=== Summary Statistics ===")
+        print(summary)
+        
+        # Create plots
+        print("\n=== Creating Visualizations ===")
+        self.plot_economic_indicators(df)
+        
+        return df, summary
+
+def main():
+    """Main function to run the FRED data analysis."""
+    collector = FREDDataCollectorV2()
+    
+    # Example: Analyze key economic indicators
+    key_indicators = ['GDP', 'UNRATE', 'CPIAUCSL', 'FEDFUNDS', 'DGS10']
+    
+    try:
+        df, summary = collector.run_analysis(series_ids=key_indicators)
+        
+        if df is not None:
+            print("\n=== Analysis Complete ===")
+            print(f"Data shape: {df.shape}")
+            print(f"Date range: {df.index.min()} to {df.index.max()}")
+        else:
+            print("\n=== Analysis Failed ===")
+        
+    except Exception as e:
+        print(f"Error during analysis: {e}")
+
+if __name__ == "__main__":
+    main() 

src/core/fred_pipeline.py

@@ -0,0 +1,88 @@
+from .base_pipeline import BasePipeline
+import requests
+import pandas as pd
+import os
+from datetime import datetime
+
+class FREDPipeline(BasePipeline):
+    """
+    FRED Data Pipeline: Extracts, transforms, and loads FRED data using config.
+    """
+    def __init__(self, config_path: str):
+        super().__init__(config_path)
+        self.fred_cfg = self.config['fred']
+        self.api_key = self.fred_cfg['api_key']
+        self.series = self.fred_cfg['series']
+        self.start_date = self.fred_cfg['start_date']
+        self.end_date = self.fred_cfg['end_date']
+        self.output_dir = self.fred_cfg['output_dir']
+        self.export_dir = self.fred_cfg['export_dir']
+        os.makedirs(self.output_dir, exist_ok=True)
+        os.makedirs(self.export_dir, exist_ok=True)
+
+    def extract(self):
+        """Extract data from FRED API for all configured series."""
+        base_url = "https://api.stlouisfed.org/fred/series/observations"
+        data = {}
+        for series_id in self.series:
+            params = {
+                'series_id': series_id,
+                'api_key': self.api_key,
+                'file_type': 'json',
+                'start_date': self.start_date,
+                'end_date': self.end_date
+            }
+            try:
+                resp = requests.get(base_url, params=params)
+                resp.raise_for_status()
+                obs = resp.json().get('observations', [])
+                dates, values = [], []
+                for o in obs:
+                    try:
+                        dates.append(pd.to_datetime(o['date']))
+                        values.append(float(o['value']) if o['value'] != '.' else None)
+                    except Exception:
+                        continue
+                data[series_id] = pd.Series(values, index=dates, name=series_id)
+                self.logger.info(f"Extracted {len(values)} records for {series_id}")
+            except Exception as e:
+                self.logger.error(f"Failed to extract {series_id}: {e}")
+        return data
+
+    def transform(self, data):
+        """Transform raw data into a DataFrame, align dates, handle missing."""
+        if not data:
+            self.logger.warning("No data to transform.")
+            return pd.DataFrame()
+        all_dates = set()
+        for s in data.values():
+            all_dates.update(s.index)
+        if not all_dates:
+            return pd.DataFrame()
+        date_range = pd.date_range(min(all_dates), max(all_dates), freq='D')
+        df = pd.DataFrame(index=date_range)
+        for k, v in data.items():
+            df[k] = v
+        df.index.name = 'Date'
+        self.logger.info(f"Transformed data to DataFrame with shape {df.shape}")
+        return df
+
+    def load(self, df):
+        """Save DataFrame to CSV in output_dir and export_dir."""
+        if df.empty:
+            self.logger.warning("No data to load.")
+            return None
+        ts = datetime.now().strftime("%Y%m%d_%H%M%S")
+        out_path = os.path.join(self.output_dir, f'fred_data_{ts}.csv')
+        exp_path = os.path.join(self.export_dir, f'fred_data_{ts}.csv')
+        df.to_csv(out_path)
+        df.to_csv(exp_path)
+        self.logger.info(f"Saved data to {out_path} and {exp_path}")
+        return out_path, exp_path
+
+    def run(self):
+        self.logger.info("Starting FRED data pipeline run...")
+        data = self.extract()
+        df = self.transform(data)
+        self.load(df)
+        self.logger.info("FRED data pipeline run complete.") 

src/utils/__init__.py

@@ -0,0 +1,7 @@
+"""
+Utility functions and helper modules.
+"""
+
+from .examples import *
+
+__all__ = ['examples'] 

src/utils/examples.py

@@ -0,0 +1,139 @@
+#!/usr/bin/env python3
+"""
+Example usage of the FRED Data Collector
+Demonstrates various ways to use the tool for economic data analysis
+"""
+
+import sys
+import os
+sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
+
+from core.fred_client import FREDDataCollectorV2
+import pandas as pd
+from datetime import datetime, timedelta
+
+def example_basic_usage():
+    """Basic usage example."""
+    print("=== Basic Usage Example ===")
+    
+    collector = FREDDataCollectorV2()
+    
+    # Get data for a single indicator
+    gdp_data = collector.get_economic_data(['GDP'], '2020-01-01', '2024-01-01')
+    df = collector.create_dataframe(gdp_data)
+    
+    print(f"GDP data shape: {df.shape}")
+    print(f"Date range: {df.index.min()} to {df.index.max()}")
+    print(f"Latest GDP value: ${df['GDP'].iloc[-1]:,.2f} billion")
+    
+    return df
+
+def example_multiple_indicators():
+    """Example with multiple economic indicators."""
+    print("\n=== Multiple Indicators Example ===")
+    
+    collector = FREDDataCollectorV2()
+    
+    # Define indicators of interest
+    indicators = ['UNRATE', 'CPIAUCSL', 'FEDFUNDS']
+    
+    # Get data for the last 5 years
+    end_date = datetime.now().strftime('%Y-%m-%d')
+    start_date = (datetime.now() - timedelta(days=5*365)).strftime('%Y-%m-%d')
+    
+    data = collector.get_economic_data(indicators, start_date, end_date)
+    df = collector.create_dataframe(data)
+    
+    # Generate summary statistics
+    summary = collector.generate_summary_statistics(df)
+    print("\nSummary Statistics:")
+    print(summary)
+    
+    # Save data
+    collector.save_data(df, 'example_multiple_indicators.csv')
+    
+    return df
+
+def example_custom_analysis():
+    """Example of custom analysis."""
+    print("\n=== Custom Analysis Example ===")
+    
+    collector = FREDDataCollectorV2()
+    
+    # Focus on monetary policy indicators
+    monetary_indicators = ['FEDFUNDS', 'DGS10', 'M2SL']
+    
+    # Get data for the last 10 years
+    end_date = datetime.now().strftime('%Y-%m-%d')
+    start_date = (datetime.now() - timedelta(days=10*365)).strftime('%Y-%m-%d')
+    
+    data = collector.get_economic_data(monetary_indicators, start_date, end_date)
+    df = collector.create_dataframe(data)
+    
+    # Calculate some custom metrics
+    if 'FEDFUNDS' in df.columns and 'DGS10' in df.columns:
+        # Calculate yield curve spread (10Y - Fed Funds)
+        df['YIELD_SPREAD'] = df['DGS10'] - df['FEDFUNDS']
+        
+        print(f"\nYield Curve Analysis:")
+        print(f"Current Fed Funds Rate: {df['FEDFUNDS'].iloc[-1]:.2f}%")
+        print(f"Current 10Y Treasury Rate: {df['DGS10'].iloc[-1]:.2f}%")
+        print(f"Current Yield Spread: {df['YIELD_SPREAD'].iloc[-1]:.2f}%")
+        
+        # Check for inverted yield curve (negative spread)
+        inverted_periods = df[df['YIELD_SPREAD'] < 0]
+        if not inverted_periods.empty:
+            print(f"Yield curve inverted for {len(inverted_periods)} periods")
+    
+    return df
+
+def example_series_info():
+    """Example of getting series information."""
+    print("\n=== Series Information Example ===")
+    
+    collector = FREDDataCollectorV2()
+    
+    # Get information about different series
+    series_to_check = ['GDP', 'UNRATE', 'CPIAUCSL']
+    
+    for series_id in series_to_check:
+        info = collector.get_series_info(series_id)
+        if info:
+            print(f"\n{series_id}:")
+            print(f"  Title: {info['title']}")
+            print(f"  Units: {info['units']}")
+            print(f"  Frequency: {info['frequency']}")
+            print(f"  Last Updated: {info['last_updated']}")
+
+def example_error_handling():
+    """Example showing error handling."""
+    print("\n=== Error Handling Example ===")
+    
+    collector = FREDDataCollectorV2()
+    
+    # Try to get data for an invalid series ID
+    invalid_series = ['INVALID_SERIES_ID']
+    
+    data = collector.get_economic_data(invalid_series)
+    print("Attempted to fetch invalid series - handled gracefully")
+
+def main():
+    """Run all examples."""
+    print("FRED Data Collector - Example Usage")
+    print("=" * 50)
+    
+    try:
+        # Run examples
+        example_basic_usage()
+        example_multiple_indicators()
+        example_custom_analysis()
+        example_series_info()
+        example_error_handling()
+        
+        print("\n=== All Examples Completed Successfully ===")
+        
+    except Exception as e:
+        print(f"Error running examples: {e}")
+
+if __name__ == "__main__":
+    main() 

src/visualization/__init__.py

@@ -0,0 +1,5 @@
+"""
+Data visualization and plotting utilities.
+"""
+
+__all__ = [] 

tests/test_fred_api.py

@@ -0,0 +1,115 @@
+#!/usr/bin/env python3
+"""
+Simple FRED API test
+"""
+
+import requests
+import sys
+import os
+sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
+
+from config.settings import FRED_API_KEY
+
+def test_fred_api_direct():
+    """Test FRED API directly using requests."""
+    print("Testing FRED API directly...")
+    
+    # Test URL for GDP series
+    url = f"https://api.stlouisfed.org/fred/series/observations"
+    params = {
+        'series_id': 'GDP',
+        'api_key': FRED_API_KEY,
+        'file_type': 'json',
+        'start_date': '2023-01-01',
+        'end_date': '2023-12-31'
+    }
+    
+    try:
+        response = requests.get(url, params=params)
+        
+        if response.status_code == 200:
+            data = response.json()
+            observations = data.get('observations', [])
+            
+            if observations:
+                print("✓ API connection successful!")
+                print(f"✓ Retrieved {len(observations)} GDP observations")
+                
+                # Get the latest observation
+                latest = observations[-1]
+                print(f"✓ Latest GDP value: ${float(latest['value']):,.2f} billion")
+                print(f"✓ Date: {latest['date']}")
+                return True
+            else:
+                print("✗ No observations found")
+                return False
+        else:
+            print(f"✗ API request failed with status code: {response.status_code}")
+            print(f"Response: {response.text}")
+            return False
+            
+    except Exception as e:
+        print(f"✗ API connection failed: {e}")
+        return False
+
+def test_series_search():
+    """Test searching for series."""
+    print("\nTesting series search...")
+    
+    url = "https://api.stlouisfed.org/fred/series/search"
+    params = {
+        'search_text': 'GDP',
+        'api_key': FRED_API_KEY,
+        'file_type': 'json'
+    }
+    
+    try:
+        response = requests.get(url, params=params)
+        
+        if response.status_code == 200:
+            data = response.json()
+            series = data.get('seriess', [])
+            
+            if series:
+                print("✓ Series search successful!")
+                print(f"✓ Found {len(series)} series matching 'GDP'")
+                
+                # Show first few results
+                for i, s in enumerate(series[:3]):
+                    print(f"  {i+1}. {s['id']}: {s['title']}")
+                return True
+            else:
+                print("✗ No series found")
+                return False
+        else:
+            print(f"✗ Search request failed: {response.status_code}")
+            return False
+            
+    except Exception as e:
+        print(f"✗ Search failed: {e}")
+        return False
+
+def main():
+    """Run simple API tests."""
+    print("Simple FRED API Test")
+    print("=" * 30)
+    print(f"API Key: {FRED_API_KEY[:8]}...")
+    print()
+    
+    # Test direct API access
+    api_ok = test_fred_api_direct()
+    
+    # Test series search
+    search_ok = test_series_search()
+    
+    print("\n" + "=" * 30)
+    if api_ok and search_ok:
+        print("✓ All tests passed! Your API key is working correctly.")
+        print("The issue is with the fredapi library, not your API key.")
+    else:
+        print("✗ Some tests failed. Please check your API key.")
+    
+    return api_ok and search_ok
+
+if __name__ == "__main__":
+    main() 

tests/test_fredapi_library.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python3
+"""
+Test script to verify FRED API key functionality
+"""
+
+from fredapi import Fred
+import sys
+import os
+sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
+
+from config.settings import FRED_API_KEY
+
+def test_api_connection():
+    """Test the FRED API connection with the provided key."""
+    print("Testing FRED API connection...")
+    
+    try:
+        # Initialize FRED client
+        fred = Fred(api_key=FRED_API_KEY)
+        
+        # Test with a simple series (GDP)
+        print("Fetching GDP data as a test...")
+        gdp_data = fred.get_series('GDP', start='2023-01-01', end='2023-12-31')
+        
+        if not gdp_data.empty:
+            print("✓ API connection successful!")
+            print(f"✓ Retrieved {len(gdp_data)} GDP observations")
+            print(f"✓ Latest GDP value: ${gdp_data.iloc[-1]:,.2f} billion")
+            print(f"✓ Date range: {gdp_data.index.min()} to {gdp_data.index.max()}")
+            return True
+        else:
+            print("✗ No data retrieved")
+            return False
+            
+    except Exception as e:
+        print(f"✗ API connection failed: {e}")
+        return False
+
+def test_series_info():
+    """Test getting series information."""
+    print("\nTesting series information retrieval...")
+    
+    try:
+        fred = Fred(api_key=FRED_API_KEY)
+        
+        # Test getting info for GDP
+        series_info = fred.get_series_info('GDP')
+        
+        print("✓ Series information retrieved successfully!")
+        print(f"  Title: {series_info.title}")
+        print(f"  Units: {series_info.units}")
+        print(f"  Frequency: {series_info.frequency}")
+        print(f"  Last Updated: {series_info.last_updated}")
+        
+        return True
+        
+    except Exception as e:
+        print(f"✗ Failed to get series info: {e}")
+        return False
+
+def main():
+    """Run API tests."""
+    print("FRED API Key Test")
+    print("=" * 30)
+    print(f"API Key: {FRED_API_KEY[:8]}...")
+    print()
+    
+    # Test connection
+    connection_ok = test_api_connection()
+    
+    # Test series info
+    info_ok = test_series_info()
+    
+    print("\n" + "=" * 30)
+    if connection_ok and info_ok:
+        print("✓ All tests passed! Your API key is working correctly.")
+        print("You can now use the FRED data collector tool.")
+    else:
+        print("✗ Some tests failed. Please check your API key.")
+    
+    return connection_ok and info_ok
+
+if __name__ == "__main__":
+    main()