PHPMem v2.0.1

Version
1.6.45
Uptime
17 days 18 hours 19 minutes 3 seconds

Memory

Total
512MB
Used
12,72MB (2.48%)
Free
499,28MB

Keys

Current
14 060
Total (since start)
40 994
Evictions
0
Reclaimed
760
Expired Unfetched
0
Evicted Unfetched
0

Connections

Current
2 / 1 024 max
Total
240 720
Rejected
0
llm:8b4e3dffdfb743950b16d1975a148b3188229e033cfc2664965544c9d9c8461f
TTL 5 days 9 hours 4 seconds Size 2,28KB Export
Edit
**The strongest relationship is between company age (Founded) and funding stage, followed by funding stage and deal size (Amount). The dataset has few numeric columns, so most of what can be related comes from these three.** The figures below come from a correlation query over 426 rows (385 with a usable amount and 256 with a stage that could be ranked). I converted Stage to an ordinal rank and used the natural log of Amount, because amounts are heavily skewed. | Pair | Correlation | Reading | |---|---|---| | Founded vs Stage | **-0.54** | Older companies are at later stages. The average founding year is about 2012–2014 for Series D–F, about 2018–2019 for Seed and Series A, and about 2021 for Pre-seed. | | Stage vs ln(Amount) | **+0.40** | Later stages raise more money. | | Founded vs ln(Amount) | **-0.25** | Older companies raise somewhat larger amounts. This is probably mostly an effect of stage. | **Stage and Amount.** The medians rise steadily with stage: - Pre-seed: about $0.5M. - Seed: about $1.6M. - Series A: $12M. - Series B: $22M. - Series C: $60M. - Series D: $71M. - Series E and F: roughly $316–364M. The correlation of 0.40 is moderate rather than strong. There is wide overlap between stages, and the "undisclosed" stage has a median of $23.5M. **Caveats on data quality** - The five monthly tables share one schema, but Amount and Stage are stored as text and are messy. - Amount is often "Undisclosed" (35 rows) or blank (25 rows). - Stage has many variants, such as "Preseed" and "Pre-seed", "Undiclosed" and "undisclosed", and "Series-D" and "Series D". - Stage also contains some misaligned values, such as investor names and "Series G" with an amount of "$165.5". - 127 rows have no Stage at all. - Some stray values were left out of the ranking, so the correlations are approximate and likely understate the true relationships. - I did not measure how Sector or Location relate to Amount or Stage. They are categorical columns with many distinct values, so any relationship there would need a grouped comparison rather than a correlation. The queries behind these figures are the stage-level summary (step 1) and the correlation query (step 2).