Skip to content

DDT_214 #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Jerad551 wants to merge 4 commits into
base: main
Choose a base branch
from
+130 −236
Open

DDT_214 #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
584058f
RUC 3130
Jerad551 Jan 15, 2026
6c6378d
4547ff632
Jerad551 Feb 7, 2026
e6eff5b
flacke8
Jerad551 Feb 23, 2026
edaa28d
<!-- IMPORTANT: Please be sure to remove any private information befo…
Jerad551 Feb 23, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions copilot-worktree-2026-01-14T11-31-32.code-workspace
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
{
"folders": [
{
"path": "."
}
],
"settings": {
"jdk.telemetry.enabled": true,
"redhat.telemetry.enabled": true
}
}
142 changes: 74 additions & 68 deletions examples/advanced_examples.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,17 +18,19 @@

def example_1_basic_workflow():
"""Example 1: Basic analysis workflow."""
print("="*70)
print("=" * 70)
print("Example 1: Basic Analysis Workflow")
print("="*70)
print("=" * 70)

# Load data
loader = CodeFrequencyLoader()
data = loader.load()

print(f"\n📊 Loaded {len(data)} records")
print(f"Date range: {data['DateTime'].min().date()} to {data['DateTime'].max().date()}")

print(
f"Date range: {data['DateTime'].min().date()} to {data['DateTime'].max().date()}"
)

# Get summary
summary = loader.get_summary()
print(f"\n📈 Summary:")
Expand All @@ -39,47 +41,49 @@ def example_1_basic_workflow():

def example_2_sprint_analysis():
"""Example 2: Detailed sprint analysis."""
print("\n" + "="*70)
print("\n" + "=" * 70)
print("Example 2: Sprint Detection and Analysis")
print("="*70)
print("=" * 70)

loader = CodeFrequencyLoader()
analyzer = CodeFrequencyAnalyzer(loader)

# Detect sprints with custom parameters
sprints = analyzer.detect_sprints(window_weeks=3, threshold_multiplier=1.5)

print(f"\n🚀 Detected {len(sprints)} coding sprints:\n")

for i, sprint in enumerate(sprints[:5], 1): # Show top 5
print(f"Sprint {i}:")
print(f" Duration: {sprint['duration_weeks']} weeks")
print(f" Period: {sprint['start_date'].date()} to {sprint['end_date'].date()}")
print(f" Total changes: {sprint['total_additions'] + sprint['total_deletions']:,}")
print(
f" Total changes: {sprint['total_additions'] + sprint['total_deletions']:,}"
)
print(f" Avg weekly churn: {sprint['avg_weekly_churn']:,.0f}")
print()


def example_3_time_analysis():
"""Example 3: Time-based analysis."""
print("="*70)
print("=" * 70)
print("Example 3: Time-Based Analysis")
print("="*70)
print("=" * 70)

loader = CodeFrequencyLoader()
analyzer = CodeFrequencyAnalyzer(loader)

# Yearly statistics
yearly = analyzer.get_yearly_stats()
print("\n📅 Top 3 Most Productive Years:")
top_years = yearly.nlargest(3, 'Additions_sum')
top_years = yearly.nlargest(3, "Additions_sum")

for year, row in top_years.iterrows():
print(f"\n{year}:")
print(f" Additions: {int(row['Additions_sum']):,}")
print(f" Deletions: {int(abs(row['Deletions_sum'])):,}")
print(f" Net: {int(row['net_changes']):,}")

# Activity patterns
print(f"\n📊 Activity Statistics:")
print(f" Activity ratio: {analyzer.calculate_activity_ratio():.2%}")
Expand All @@ -90,74 +94,76 @@ def example_3_time_analysis():

def example_4_custom_visualization():
"""Example 4: Custom visualization."""
print("\n" + "="*70)
print("\n" + "=" * 70)
print("Example 4: Custom Visualization")
print("="*70)
print("=" * 70)

loader = CodeFrequencyLoader()
loader.load()
data = loader.data.copy()

# Create custom analysis
data['NetChanges'] = data['Additions'] + data['Deletions']
data['Year'] = data['DateTime'].dt.year
data["NetChanges"] = data["Additions"] + data["Deletions"]
data["Year"] = data["DateTime"].dt.year

# Calculate moving average
data['MA_30'] = data['Additions'].rolling(window=30, center=True).mean()
data["MA_30"] = data["Additions"].rolling(window=30, center=True).mean()

# Create custom plot
fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(14, 8))

# Plot 1: Additions with moving average
ax1.plot(data['DateTime'], data['Additions'], alpha=0.3, label='Additions')
ax1.plot(data['DateTime'], data['MA_30'], 'r-', linewidth=2, label='30-week MA')
ax1.set_ylabel('Lines Added')
ax1.set_title('Code Additions with 30-Week Moving Average')
ax1.plot(data["DateTime"], data["Additions"], alpha=0.3, label="Additions")
ax1.plot(data["DateTime"], data["MA_30"], "r-", linewidth=2, label="30-week MA")
ax1.set_ylabel("Lines Added")
ax1.set_title("Code Additions with 30-Week Moving Average")
ax1.legend()
ax1.grid(True, alpha=0.3)

# Plot 2: Net changes by year
yearly_net = data.groupby('Year')['NetChanges'].sum()
ax2.bar(yearly_net.index, yearly_net.values, color='steelblue', alpha=0.7)
ax2.axhline(y=0, color='black', linestyle='-', linewidth=0.5)
ax2.set_xlabel('Year')
ax2.set_ylabel('Net Changes')
ax2.set_title('Net Code Changes by Year')
ax2.grid(True, alpha=0.3, axis='y')
yearly_net = data.groupby("Year")["NetChanges"].sum()
ax2.bar(yearly_net.index, yearly_net.values, color="steelblue", alpha=0.7)
ax2.axhline(y=0, color="black", linestyle="-", linewidth=0.5)
ax2.set_xlabel("Year")
ax2.set_ylabel("Net Changes")
ax2.set_title("Net Code Changes by Year")
ax2.grid(True, alpha=0.3, axis="y")

plt.tight_layout()

# Save plot
output_path = Path('output/visualizations/custom_analysis.png')
output_path = Path("output/visualizations/custom_analysis.png")
output_path.parent.mkdir(parents=True, exist_ok=True)
plt.savefig(output_path, dpi=300, bbox_inches='tight')
plt.savefig(output_path, dpi=300, bbox_inches="tight")
print(f"\n✅ Custom visualization saved to {output_path}")
plt.close()


def example_5_filtering_analysis():
"""Example 5: Filtering and conditional analysis."""
print("\n" + "="*70)
print("\n" + "=" * 70)
print("Example 5: Filtering and Conditional Analysis")
print("="*70)
print("=" * 70)

loader = CodeFrequencyLoader()
loader.load()
data = loader.data.copy()

# Analyze only high-activity periods
data['AbsChanges'] = data['Additions'] + abs(data['Deletions'])
high_activity = data[data['AbsChanges'] > data['AbsChanges'].quantile(0.75)]
data["AbsChanges"] = data["Additions"] + abs(data["Deletions"])
high_activity = data[data["AbsChanges"] > data["AbsChanges"].quantile(0.75)]

print(f"\n📊 High Activity Periods (top 25%):")
print(f" Total records: {len(high_activity)}")
print(f" Date range: {high_activity['DateTime'].min().date()} to {high_activity['DateTime'].max().date()}")
print(
f" Date range: {high_activity['DateTime'].min().date()} to {high_activity['DateTime'].max().date()}"
)
print(f" Total changes: {high_activity['AbsChanges'].sum():,.0f}")

# Analyze recent activity (last 2 years)
recent_date = data['DateTime'].max() - pd.Timedelta(days=730)
recent_data = data[data['DateTime'] >= recent_date]
recent_date = data["DateTime"].max() - pd.Timedelta(days=730)
recent_data = data[data["DateTime"] >= recent_date]

print(f"\n📅 Recent Activity (last 2 years):")
print(f" Records: {len(recent_data)}")
print(f" Total additions: {recent_data['Additions'].sum():,}")
Expand All @@ -167,16 +173,16 @@ def example_5_filtering_analysis():

def example_6_comparison_analysis():
"""Example 6: Comparative analysis."""
print("\n" + "="*70)
print("\n" + "=" * 70)
print("Example 6: Comparative Analysis")
print("="*70)
print("=" * 70)

loader = CodeFrequencyLoader()
analyzer = CodeFrequencyAnalyzer(loader)

# Compare productivity across time periods
trends = analyzer.get_productivity_trends(periods=4)

print("\n📊 Productivity Trends (4 periods):")
for period, row in trends.iterrows():
print(f"\nPeriod {period + 1}:")
Expand All @@ -193,19 +199,19 @@ def main():
print("║ 📚 RunTime Advanced Examples 📚 ║")
print("║ ║")
print("╚═══════════════════════════════════════════════════════════════╝\n")

try:
example_1_basic_workflow()
example_2_sprint_analysis()
example_3_time_analysis()
example_4_custom_visualization()
example_5_filtering_analysis()
example_6_comparison_analysis()
print("\n" + "="*70)

print("\n" + "=" * 70)
print("✅ All examples completed successfully!")
print("="*70)
print("=" * 70)

except Exception as e:
print(f"\n❌ Error: {e}")
raise
Expand Down
81 changes: 10 additions & 71 deletions notebooks/exploration.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -610,80 +610,19 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": 1,
"id": "7be2de20",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Found 8 coding sprints:\n",
"\n",
"Sprint 1:\n",
" start_date: 2018-03-11 00:00:00\n",
" end_date: 2018-04-22 00:00:00\n",
" duration_weeks: 7\n",
" total_additions: 817757\n",
" total_deletions: 219662\n",
" avg_weekly_churn: 148202.7142857143\n",
"\n",
"Sprint 2:\n",
" start_date: 2018-05-20 00:00:00\n",
" end_date: 2018-06-10 00:00:00\n",
" duration_weeks: 4\n",
" total_additions: 135273\n",
" total_deletions: 527\n",
" avg_weekly_churn: 33950.0\n",
"\n",
"Sprint 3:\n",
" start_date: 2018-07-22 00:00:00\n",
" end_date: 2018-08-12 00:00:00\n",
" duration_weeks: 4\n",
" total_additions: 138173\n",
" total_deletions: 110270\n",
" avg_weekly_churn: 62110.75\n",
"\n",
"Sprint 4:\n",
" start_date: 2019-06-02 00:00:00\n",
" end_date: 2019-06-23 00:00:00\n",
" duration_weeks: 4\n",
" total_additions: 62\n",
" total_deletions: 219657\n",
" avg_weekly_churn: 54929.75\n",
"\n",
"Sprint 5:\n",
" start_date: 2019-11-03 00:00:00\n",
" end_date: 2019-11-24 00:00:00\n",
" duration_weeks: 4\n",
" total_additions: 44861\n",
" total_deletions: 767311\n",
" avg_weekly_churn: 203043.0\n",
"\n",
"Sprint 6:\n",
" start_date: 2021-05-23 00:00:00\n",
" end_date: 2021-06-13 00:00:00\n",
" duration_weeks: 4\n",
" total_additions: 88404\n",
" total_deletions: 77108\n",
" avg_weekly_churn: 41378.0\n",
"\n",
"Sprint 7:\n",
" start_date: 2021-11-28 00:00:00\n",
" end_date: 2021-11-28 00:00:00\n",
" duration_weeks: 1\n",
" total_additions: 0\n",
" total_deletions: 0\n",
" avg_weekly_churn: 0.0\n",
"\n",
"Sprint 8:\n",
" start_date: 2022-02-13 00:00:00\n",
" end_date: 2022-03-06 00:00:00\n",
" duration_weeks: 4\n",
" total_additions: 9613\n",
" total_deletions: 54794\n",
" avg_weekly_churn: 16101.75\n",
"\n"
"ename": "NameError",
"evalue": "name 'analyzer' is not defined",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mNameError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[1]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m sprints = \u001b[43manalyzer\u001b[49m.detect_sprints()\n\u001b[32m 3\u001b[39m \u001b[38;5;28mprint\u001b[39m(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mFound \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(sprints)\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m coding sprints:\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[33m\"\u001b[39m)\n\u001b[32m 4\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m i, sprint \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(sprints, \u001b[32m1\u001b[39m):\n",
"\u001b[31mNameError\u001b[39m: name 'analyzer' is not defined"
]
}
],
Expand Down Expand Up @@ -816,7 +755,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
Expand Down
Binary file modified src/__pycache__/load_data.cpython-312.pyc
View file
Open in desktop
Binary file not shown.
Loading