================================================================================
DESCRIPTIVE STATISTICS AND SUMMARY ANALYSIS
================================================================================

Dataset Shape: 557 rows × 19 columns

DATA QUALITY SUMMARY
--------------------------------------------------------------------------------
Total columns: 19
Columns with >50% missing data: 11
Columns with >90% missing data: 9

Columns with high missing data (>50%): Unnamed__4, Unnamed__5, Unnamed__6, Unnamed__7, Number_of_animals_arrived_, Unnamed__9, Unnamed__10, Unnamed__11, Unnamed__12, Unnamed__13, Unnamed__18


NUMERIC VARIABLES ANALYSIS
--------------------------------------------------------------------------------
Number of numeric columns analyzed: 5

P24003_CAGE_numeric:
  Mean: 2368.17
  Median: 3607.00
  Std Dev: 1500.78
  Range: [326.33, 3881.00]
  Missing: 8 (1.4%)

Unnamed__4_numeric:
  Mean: 328.22
  Median: 329.00
  Std Dev: 31.79
  Range: [248.00, 419.00]
  Missing: 317 (56.9%)

P24003_CAGE_1_numeric:
  Mean: 2391.07
  Median: 3610.00
  Std Dev: 1493.06
  Range: [382.30, 3881.00]
  Missing: 14 (2.5%)

Unnamed__18_numeric:
  Mean: 328.22
  Median: 329.00
  Std Dev: 31.79
  Range: [248.00, 419.00]
  Missing: 317 (56.9%)


CATEGORICAL VARIABLES ANALYSIS
--------------------------------------------------------------------------------
Number of categorical columns analyzed: 6

Trial_code:
  Unique values: 14
  Most frequent: 'P24015-CAGE' (300 occurrences)
  Missing: 5 (0.9%)

Unnamed__2:
  Unique values: 21
  Most frequent: 'T02' (60 occurrences)
  Missing: 6 (1.1%)

Unnamed__3:
  Unique values: 61
  Most frequent: 'T08-4' (10 occurrences)
  Missing: 16 (2.9%)

Trial_code_1:
  Unique values: 14
  Most frequent: 'P24015-CAGE' (300 occurrences)
  Missing: 5 (0.9%)

Unnamed__16:
  Unique values: 15
  Most frequent: 'T02' (60 occurrences)
  Missing: 12 (2.2%)


OVERALL DATASET SUMMARY
--------------------------------------------------------------------------------
Total observations: 557
Total variables: 23
Numeric variables: 5
Categorical variables: 18

Data completeness: 0.0% complete rows
Total missing values: 6336 (49.46%)


KEY FINDINGS
--------------------------------------------------------------------------------

1. High Missing Data Alert:
   9 columns have >90% missing data.
   These columns may not be useful for analysis.

2. Most Complete Columns:
   8 columns have <10% missing data.
   These are the most reliable for analysis.

3. Data Type Distribution:
   Object/String columns: 18
   Numeric columns: 5


RECOMMENDATIONS
--------------------------------------------------------------------------------
1. Consider removing columns with >90% missing data
2. Investigate the cause of missing data patterns
3. Focus analysis on columns with <20% missing data
4. Consider data imputation strategies for important variables
5. Verify data types and convert where appropriate

================================================================================
END OF ANALYSIS
================================================================================