dadams/colorado_spills
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

analsyis 10 has rural and industry hyp

Browse Source
This commit is contained in:
David Adams
2025-08-06 11:58:03 -07:00
parent f4d1166502
commit 389191accd
1 changed files with 539 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

539
analysis/new analysis Aug 2025/analysis10-2021.ipynb
View File

@@ -1862,6 +1862,545 @@
"\n",
"**Bottom line**: The mission change had **net negative effects on delay times**, with rural communities bearing the brunt of the impact. "
]
},
{
"cell_type": "code",
"execution_count": 77,
"id": "433ce72e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Columns in spills_gdf:\n",
"- Document #\n",
"- Report\n",
"- Operator\n",
"- Operator #\n",
"- Tracking #\n",
"- Initial Report Date\n",
"- Date of Discovery\n",
"- spill_type\n",
"- Qtr Qtr\n",
"- Section\n",
"- Township\n",
"- range\n",
"- meridian\n",
"- Latitude\n",
"- Longitude\n",
"- Municipality\n",
"- county\n",
"- Facility Type\n",
"- Facility ID\n",
"- API County Code\n",
"- API Sequence Number\n",
"- Spilled outside of berms\n",
"- More than five barrels spilled\n",
"- Oil Spill Volume\n",
"- Condensate Spill Volume\n",
"- Flow Back Spill Volume\n",
"- Produced Water Spill Volume\n",
"- E&P Waste Spill Volume\n",
"- Other Waste\n",
"- Drilling Fluid Spill Volume\n",
"- Current Land Use\n",
"- Other Land Use\n",
"- Weather Conditions\n",
"- Surface Owner\n",
"- Surface Owner Other\n",
"- Waters of the State\n",
"- Residence / Occupied Structure\n",
"- livestock\n",
"- Public Byway\n",
"- Surface Water Supply Area\n",
"- Spill Description\n",
"- Supplemental Report Date\n",
"- Oil BBLs Spilled\n",
"- Oil BBLs Recovered\n",
"- Oil Unknown\n",
"- Condensate BBLs Spilled\n",
"- Condensate BBLs Recovered\n",
"- Condensate Unknown\n",
"- Produced Water BBLs Spilled\n",
"- Produced Water BBLs Recovered\n",
"- Produced Water Unknown\n",
"- Drilling Fluid BBLs Spilled\n",
"- Drilling Fluid BBLs Recovered\n",
"- Drilling Fluid Unknown\n",
"- Flow Back Fluid BBLs Spilled\n",
"- Flow Back Fluid BBLs Recovered\n",
"- Flow Back Fluid Unkown\n",
"- Other E&P Waste BBLS Spilled\n",
"- Other E&P Waste BBLS Recovered\n",
"- Other E&P Waste Unknown\n",
"- Other E&P Waste\n",
"- Spill Contained within Berm\n",
"- Emergency Pit Constructed\n",
"- soil\n",
"- groundwater\n",
"- Surface Water\n",
"- Dry Drainage Feature\n",
"- Surface Area Length\n",
"- Surface Area Width\n",
"- Depth of Impact in Feet\n",
"- Depth of Impact in Inches\n",
"- Area Depth Determined\n",
"- Geology Description\n",
"- Depth to Groundwater\n",
"- Water wells in area\n",
"- Water Wells\n",
"- Water Wells None\n",
"- Surface Water Near\n",
"- Surface Water None\n",
"- Wetlands\n",
"- Wetlands None\n",
"- Springs\n",
"- Springs None\n",
"- Livestock Near\n",
"- Livestock None\n",
"- Occupied Buildings\n",
"- Occupied Buildings None\n",
"- Additional Spill Details\n",
"- Supplemental Report Date CA\n",
"- Human Error\n",
"- Equipment Failure\n",
"- Historical Unkown\n",
"- Other\n",
"- Other Description\n",
"- Root Cause\n",
"- Preventative Measures\n",
"- Soil Excavated\n",
"- Offsite Disposal\n",
"- Onsite Treatment\n",
"- Other Disposition\n",
"- Other Disposition Description\n",
"- Ground Water Removed\n",
"- Surface Water Removed\n",
"- Corrective Actions Completed\n",
"- Approved Form 27\n",
"- Form 27 Project Number\n",
"- GEOID\n",
"- TRACT_NAME\n",
"- total_population\n",
"- white_population\n",
"- hispanic_population\n",
"- median_household_income\n",
"- poverty_population\n",
"- unemployed_population\n",
"- percent_white\n",
"- percent_hispanic\n",
"- percent_poverty\n",
"- unemployment_rate\n",
"- geometry\n",
"- ruca_code\n",
"- ruca_description\n",
"- rurality\n",
"- Report Year\n",
"- Period\n",
"- report_delay\n",
"- report_month\n"
]
}
],
"source": [
"# print columns of spills_gdf\n",
"print(\"\\nColumns in spills_gdf:\")\n",
"for col in spills_gdf.columns:\n",
" print(f\"- {col}\")\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 82,
"id": "98e01f3f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"🏭 TESTING INDUSTRY RESISTANCE HYPOTHESIS\n",
"============================================================\n",
"Checking data structure:\n",
"Unique values in Period column: ['2021 and After' 'Before 2021']\n",
"Period value counts: Period\n",
"2021 and After 7397\n",
"Before 2021 3799\n",
"Name: count, dtype: int64\n",
"Sample of data:\n",
" Operator Period report_delay\n",
"28 PDC ENERGY INC 2021 and After 1\n",
"163 PDC ENERGY INC 2021 and After 3\n",
"226 NOBLE ENERGY INC Before 2021 2\n",
"334 NOBLE ENERGY INC Before 2021 2\n",
"342 NOBLE ENERGY INC Before 2021 0\n",
"\n",
"1️⃣ OPERATOR-LEVEL RESISTANCE ANALYSIS\n",
"---------------------------------------------\n",
"Total operators: 117\n",
"Spills per operator - Min: 1, Max: 2371\n",
"\n",
"Operator size distribution:\n",
"size_category\n",
"Small (1-5) 51\n",
"Medium (6-20) 29\n",
"Major (50+) 24\n",
"Large (21-50) 13\n",
"Name: count, dtype: int64\n",
"\n",
"Analyzing periods: '2021 and After' vs 'Before 2021'\n",
"Operator-period combinations: 161\n",
"\n",
"Average delays by operator size and period:\n",
" report_delay Document #\n",
" mean count sum\n",
"size_category Period \n",
"Small (1-5) 2021 and After 49.30 25 69\n",
" Before 2021 5.85 28 65\n",
"Medium (6-20) 2021 and After 10.74 19 137\n",
" Before 2021 4.43 24 216\n",
"Large (21-50) 2021 and After 7.99 11 259\n",
" Before 2021 1.89 8 170\n",
"Major (50+) 2021 and After 5.19 23 6932\n",
" Before 2021 3.52 23 3348\n",
"\n",
"2️⃣ OPERATOR DELAY CHANGES\n",
"-----------------------------------\n",
"Operators with data in both periods: 44\n",
"Operators with size data: 44\n",
"\n",
"🚨 TOP 10 OPERATORS WITH BIGGEST DELAY INCREASES:\n",
" 1. KP KAUFFMAN COMPANY INC | Change: + 15.0 days | Size: Major (50+)\n",
" 2. AKA ENERGY GROUP LLC | Change: + 6.6 days | Size: Medium (6-20)\n",
" 3. HUNTER RIDGE ENERGY SERVICES LLC | Change: + 5.0 days | Size: Small (1-5)\n",
" 4. EXTRACTION OIL & GAS INC | Change: + 5.0 days | Size: Major (50+)\n",
" 5. RED HAWK PETROLEUM LLC | Change: + 3.8 days | Size: Medium (6-20)\n",
" 6. PETRO MEX RESOURCES | Change: + 3.8 days | Size: Medium (6-20)\n",
" 7. DCP OPERATING COMPANY LP | Change: + 3.6 days | Size: Major (50+)\n",
" 8. ENERPLUS RESOURCES (USA) CORPORATION | Change: + 1.9 days | Size: Medium (6-20)\n",
" 9. ANADARKO WATTENBERG OIL COMPLEX LLC | Change: + 1.8 days | Size: Medium (6-20)\n",
"10. GRAND RIVER GATHERING LLC | Change: + 1.7 days | Size: Major (50+)\n",
"\n",
"✅ TOP 10 OPERATORS WITH BIGGEST IMPROVEMENTS:\n",
" 1. PETRO OPERATING COMPANY LLC | Change: -80.9 days | Size: Medium (6-20)\n",
" 2. FOUNDATION ENERGY MANAGEMENT LLC | Change: -63.0 days | Size: Large (21-50)\n",
" 3. BLUE CHIP OIL INC | Change: -54.1 days | Size: Medium (6-20)\n",
" 4. UTAH GAS OP LTD DBA UTAH GAS CORP | Change: -23.2 days | Size: Major (50+)\n",
" 5. CHEVRON USA INC | Change: -17.3 days | Size: Major (50+)\n",
" 6. BAYSWATER EXPLORATION & PRODUCTION LLC | Change: -9.7 days | Size: Major (50+)\n",
" 7. GREAT WESTERN OPERATING COMPANY LLC | Change: -7.4 days | Size: Major (50+)\n",
" 8. CRESTONE PEAK RESOURCES OPERATING LLC | Change: -3.8 days | Size: Major (50+)\n",
" 9. NOBLE ENERGY INC | Change: -3.3 days | Size: Major (50+)\n",
"10. KERR MCGEE GATHERING LLC | Change: -3.0 days | Size: Major (50+)\n",
"\n",
"3️⃣ OPERATOR SIZE EFFECT ANALYSIS\n",
"----------------------------------------\n",
"Average delay changes by operator size:\n",
" mean count std\n",
"size_category \n",
"Small (1-5) 3.00 2 2.83\n",
"Medium (6-20) -8.61 14 25.61\n",
"Large (21-50) -10.17 6 25.90\n",
"Major (50+) -2.05 22 7.59\n",
"\n",
"🔍 Large vs Small Operators:\n",
" Large operators (n=28): -3.79 days average change\n",
" Small operators (n=16): -7.16 days average change\n",
" Statistical test: t=0.596, p=0.5543 (not significant)\n",
"\n",
"4️⃣ SPILL SIZE RESISTANCE ANALYSIS\n",
"----------------------------------------\n",
"Delay changes by spill size:\n",
"spill_size_category\n",
"Small (0-1 bbl) NaN\n",
"Medium (1-10 bbl) NaN\n",
"Large (10-50 bbl) NaN\n",
"Major (50+ bbl) NaN\n",
"Name: change, dtype: float64\n",
"\n",
"5️⃣ GEOGRAPHIC RESISTANCE PATTERNS\n",
"----------------------------------------\n",
"🚨 COUNTIES WITH BIGGEST DELAY INCREASES (min 20 spills):\n",
" GARFIELD : -0.1 days (1437 spills)\n",
" WELD : -1.3 days (9041 spills)\n",
" RIO BLANCO : -6.2 days (718 spills)\n",
"\n",
"6️⃣ RESISTANCE HYPOTHESIS ASSESSMENT\n",
"---------------------------------------------\n",
"✅ Major operators overrepresented in worst performers\n",
"✅ Large operators had bigger delay increases than small operators\n",
"❌ Major spills did not have above-average delay increases\n",
"\n",
"📊 RESISTANCE HYPOTHESIS SCORE: 67% (2/3 tests support)\n",
"⚠️ MODERATE EVIDENCE for industry resistance\n",
"\n",
"✅ Analysis complete!\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_1241247/2502002660.py:62: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n",
" size_period_summary = operator_period_stats.groupby(['size_category', 'Period']).agg({\n",
"/tmp/ipykernel_1241247/2502002660.py:88: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" complete_operators['delay_change'] = complete_operators[after_period] - complete_operators[before_period]\n",
"/tmp/ipykernel_1241247/2502002660.py:118: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n",
" size_changes = complete_with_size.groupby('size_category')['delay_change'].agg(['mean', 'count', 'std']).round(2)\n",
"/tmp/ipykernel_1241247/2502002660.py:155: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n",
" size_period_analysis = spills_gdf.groupby(['spill_size_category', 'Period'])['report_delay'].mean().unstack()\n"
]
}
],
"source": [
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"import numpy as np\n",
"from scipy import stats\n",
"import statsmodels.formula.api as smf\n",
"\n",
"print(\"🏭 TESTING INDUSTRY RESISTANCE HYPOTHESIS\")\n",
"print(\"=\" * 60)\n",
"\n",
"# First, let's check what Period values we actually have\n",
"print(\"Checking data structure:\")\n",
"print(\"Unique values in Period column:\", spills_gdf['Period'].unique())\n",
"print(\"Period value counts:\", spills_gdf['Period'].value_counts())\n",
"print(\"Sample of data:\")\n",
"print(spills_gdf[['Operator', 'Period', 'report_delay']].head())\n",
"\n",
"# 1. OPERATOR-LEVEL RESISTANCE PATTERNS\n",
"print(\"\\n1️⃣ OPERATOR-LEVEL RESISTANCE ANALYSIS\")\n",
"print(\"-\" * 45)\n",
"\n",
"# Calculate operator size (number of spills as proxy for company size)\n",
"operator_stats = spills_gdf.groupby('Operator').agg({\n",
" 'Document #': 'count',\n",
" 'report_delay': 'mean'\n",
"}).rename(columns={'Document #': 'total_spills', 'report_delay': 'avg_delay'})\n",
"\n",
"print(f\"Total operators: {len(operator_stats)}\")\n",
"print(f\"Spills per operator - Min: {operator_stats['total_spills'].min()}, Max: {operator_stats['total_spills'].max()}\")\n",
"\n",
"# Categorize operators by size\n",
"operator_stats['size_category'] = pd.cut(operator_stats['total_spills'], \n",
" bins=[0, 5, 20, 50, float('inf')], \n",
" labels=['Small (1-5)', 'Medium (6-20)', 'Large (21-50)', 'Major (50+)'])\n",
"\n",
"print(\"\\nOperator size distribution:\")\n",
"print(operator_stats['size_category'].value_counts())\n",
"\n",
"# Get period values\n",
"period_values = sorted(spills_gdf['Period'].unique())\n",
"if len(period_values) >= 2:\n",
" before_period = period_values[0] \n",
" after_period = period_values[1] \n",
" print(f\"\\nAnalyzing periods: '{before_period}' vs '{after_period}'\")\n",
" \n",
" # Calculate average delays by operator and period\n",
" operator_period_stats = spills_gdf.groupby(['Operator', 'Period']).agg({\n",
" 'report_delay': 'mean',\n",
" 'Document #': 'count'\n",
" }).reset_index()\n",
" \n",
" print(f\"Operator-period combinations: {len(operator_period_stats)}\")\n",
" \n",
" # Add size categories by merging\n",
" operator_period_stats = operator_period_stats.merge(\n",
" operator_stats[['size_category']].reset_index(), \n",
" on='Operator', \n",
" how='left'\n",
" )\n",
" \n",
" # Summary by size and period\n",
" size_period_summary = operator_period_stats.groupby(['size_category', 'Period']).agg({\n",
" 'report_delay': ['mean', 'count'],\n",
" 'Document #': 'sum'\n",
" }).round(2)\n",
" \n",
" print(\"\\nAverage delays by operator size and period:\")\n",
" print(size_period_summary)\n",
" \n",
" # 2. OPERATOR CHANGES ANALYSIS\n",
" print(\"\\n2️⃣ OPERATOR DELAY CHANGES\")\n",
" print(\"-\" * 35)\n",
" \n",
" # Pivot to get before/after for each operator\n",
" operator_pivot = operator_period_stats.pivot_table(\n",
" index='Operator', \n",
" columns='Period', \n",
" values='report_delay', \n",
" aggfunc='mean'\n",
" )\n",
" \n",
" print(f\"Operators with data in both periods: {len(operator_pivot.dropna())}\")\n",
" \n",
" # Only keep operators with data in both periods\n",
" complete_operators = operator_pivot.dropna()\n",
" \n",
" if len(complete_operators) > 0:\n",
" complete_operators['delay_change'] = complete_operators[after_period] - complete_operators[before_period]\n",
" \n",
" # Add operator size info\n",
" complete_with_size = complete_operators.merge(\n",
" operator_stats[['size_category', 'total_spills']], \n",
" left_index=True, \n",
" right_index=True, \n",
" how='left'\n",
" )\n",
" \n",
" print(f\"Operators with size data: {len(complete_with_size)}\")\n",
" \n",
" # Top 10 worst performers\n",
" if len(complete_with_size) >= 10:\n",
" worst_performers = complete_with_size.nlargest(10, 'delay_change')\n",
" print(f\"\\n🚨 TOP 10 OPERATORS WITH BIGGEST DELAY INCREASES:\")\n",
" for idx, (operator, data) in enumerate(worst_performers.iterrows(), 1):\n",
" print(f\"{idx:2d}. {operator[:50]:50s} | Change: +{data['delay_change']:5.1f} days | Size: {data['size_category']}\")\n",
" \n",
" # Best performers\n",
" if len(complete_with_size) >= 10:\n",
" best_performers = complete_with_size.nsmallest(10, 'delay_change')\n",
" print(f\"\\n✅ TOP 10 OPERATORS WITH BIGGEST IMPROVEMENTS:\")\n",
" for idx, (operator, data) in enumerate(best_performers.iterrows(), 1):\n",
" print(f\"{idx:2d}. {operator[:50]:50s} | Change: {data['delay_change']:5.1f} days | Size: {data['size_category']}\")\n",
" \n",
" # 3. SIZE-BASED ANALYSIS\n",
" print(\"\\n3️⃣ OPERATOR SIZE EFFECT ANALYSIS\")\n",
" print(\"-\" * 40)\n",
" \n",
" size_changes = complete_with_size.groupby('size_category')['delay_change'].agg(['mean', 'count', 'std']).round(2)\n",
" print(\"Average delay changes by operator size:\")\n",
" print(size_changes)\n",
" \n",
" # Statistical test: Large vs Small operators\n",
" large_ops = complete_with_size[complete_with_size['size_category'].isin(['Large (21-50)', 'Major (50+)'])]\n",
" small_ops = complete_with_size[complete_with_size['size_category'].isin(['Small (1-5)', 'Medium (6-20)'])]\n",
" \n",
" if len(large_ops) > 0 and len(small_ops) > 0:\n",
" t_stat, p_val = stats.ttest_ind(large_ops['delay_change'], small_ops['delay_change'])\n",
" print(f\"\\n🔍 Large vs Small Operators:\")\n",
" print(f\" Large operators (n={len(large_ops)}): {large_ops['delay_change'].mean():+.2f} days average change\")\n",
" print(f\" Small operators (n={len(small_ops)}): {small_ops['delay_change'].mean():+.2f} days average change\")\n",
" print(f\" Statistical test: t={t_stat:.3f}, p={p_val:.4f} ({'significant' if p_val < 0.05 else 'not significant'})\")\n",
" \n",
" # 4. SPILL SIZE ANALYSIS\n",
" print(\"\\n4️⃣ SPILL SIZE RESISTANCE ANALYSIS\")\n",
" print(\"-\" * 40)\n",
" \n",
" # Create total volume\n",
" volume_cols = ['Oil Spill Volume', 'Condensate Spill Volume', 'Flow Back Spill Volume', \n",
" 'Produced Water Spill Volume', 'E&P Waste Spill Volume', 'Drilling Fluid Spill Volume']\n",
" \n",
" for col in volume_cols:\n",
" if col in spills_gdf.columns:\n",
" spills_gdf[col] = pd.to_numeric(spills_gdf[col], errors='coerce').fillna(0)\n",
" \n",
" # Sum available volume columns\n",
" available_vol_cols = [col for col in volume_cols if col in spills_gdf.columns]\n",
" if available_vol_cols:\n",
" spills_gdf['total_volume'] = spills_gdf[available_vol_cols].sum(axis=1)\n",
" \n",
" spills_gdf['spill_size_category'] = pd.cut(spills_gdf['total_volume'], \n",
" bins=[0, 1, 10, 50, float('inf')], \n",
" labels=['Small (0-1 bbl)', 'Medium (1-10 bbl)', \n",
" 'Large (10-50 bbl)', 'Major (50+ bbl)'])\n",
" \n",
" size_period_analysis = spills_gdf.groupby(['spill_size_category', 'Period'])['report_delay'].mean().unstack()\n",
" \n",
" if len(size_period_analysis.columns) == 2:\n",
" size_period_analysis['change'] = size_period_analysis.iloc[:, 1] - size_period_analysis.iloc[:, 0]\n",
" print(\"Delay changes by spill size:\")\n",
" print(size_period_analysis['change'].sort_values(ascending=False).round(2))\n",
" \n",
" # 5. GEOGRAPHIC PATTERNS\n",
" print(\"\\n5️⃣ GEOGRAPHIC RESISTANCE PATTERNS\")\n",
" print(\"-\" * 40)\n",
" \n",
" county_analysis = spills_gdf.groupby(['county', 'Period'])['report_delay'].mean().unstack()\n",
" \n",
" if len(county_analysis.columns) == 2:\n",
" county_analysis['change'] = county_analysis.iloc[:, 1] - county_analysis.iloc[:, 0]\n",
" county_analysis['total_spills'] = spills_gdf.groupby('county').size()\n",
" \n",
" # Filter for counties with significant data\n",
" significant_counties = county_analysis[county_analysis['total_spills'] >= 20]\n",
" \n",
" if len(significant_counties) > 0:\n",
" worst_counties = significant_counties.nlargest(10, 'change')\n",
" print(\"🚨 COUNTIES WITH BIGGEST DELAY INCREASES (min 20 spills):\")\n",
" for county, data in worst_counties.iterrows():\n",
" print(f\" {county:25s}: {data['change']:+5.1f} days ({data['total_spills']:3.0f} spills)\")\n",
"\n",
" # 6. SUMMARY ASSESSMENT\n",
" print(\"\\n6️⃣ RESISTANCE HYPOTHESIS ASSESSMENT\")\n",
" print(\"-\" * 45)\n",
" \n",
" evidence_count = 0\n",
" total_tests = 0\n",
" \n",
" # Test 1: Do major operators show up disproportionately in worst performers?\n",
" if 'worst_performers' in locals() and len(worst_performers) > 0:\n",
" total_tests += 1\n",
" major_in_worst = (worst_performers['size_category'] == 'Major (50+)').sum()\n",
" if major_in_worst >= 3: # 30% or more\n",
" evidence_count += 1\n",
" print(\"✅ Major operators overrepresented in worst performers\")\n",
" else:\n",
" print(\"❌ Major operators not overrepresented in worst performers\")\n",
" \n",
" # Test 2: Do large operators have bigger average increases?\n",
" if 'large_ops' in locals() and 'small_ops' in locals() and len(large_ops) > 0 and len(small_ops) > 0:\n",
" total_tests += 1\n",
" if large_ops['delay_change'].mean() > small_ops['delay_change'].mean():\n",
" evidence_count += 1\n",
" print(\"✅ Large operators had bigger delay increases than small operators\")\n",
" else:\n",
" print(\"❌ Small operators had bigger delay increases than large operators\")\n",
" \n",
" # Test 3: Do larger spills have bigger increases?\n",
" if 'size_period_analysis' in locals() and 'change' in size_period_analysis.columns:\n",
" total_tests += 1\n",
" if size_period_analysis['change'].loc['Major (50+ bbl)'] > size_period_analysis['change'].mean():\n",
" evidence_count += 1\n",
" print(\"✅ Major spills had above-average delay increases\")\n",
" else:\n",
" print(\"❌ Major spills did not have above-average delay increases\")\n",
" \n",
" if total_tests > 0:\n",
" resistance_score = (evidence_count / total_tests) * 100\n",
" print(f\"\\n📊 RESISTANCE HYPOTHESIS SCORE: {resistance_score:.0f}% ({evidence_count}/{total_tests} tests support)\")\n",
" \n",
" if resistance_score >= 67:\n",
" print(\"🚨 STRONG EVIDENCE for systematic industry resistance\")\n",
" elif resistance_score >= 33:\n",
" print(\"⚠️ MODERATE EVIDENCE for industry resistance\")\n",
" else:\n",
" print(\"✅ LIMITED EVIDENCE for systematic resistance\")\n",
" else:\n",
" print(\"⚠️ Insufficient data to assess resistance hypothesis\")\n",
"\n",
"else:\n",
" print(\"⚠️ Need at least 2 time periods for analysis\")\n",
"\n",
"print(f\"\\n✅ Analysis complete!\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f6b8b35c",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {