Skip to content
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

Uncorrelation #5

Closed
wants to merge 7 commits into from
+70 −31
Closed

Uncorrelation #5

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7a89b15
output for correlation analysis
Jul 31, 2021
970bef2
skip uncorrelation if threshold is 0
Jul 31, 2021
d7840cb
uncorrelation thresholds for dhdl correlators
Jul 31, 2021
efe0884
update readme
Jul 31, 2021
3b4cbe9
python 3 string formatting
dnlbauer Aug 2, 2021
5c41cc2
warnings use warnings.warn
dnlbauer Aug 2, 2021
639a5d5
baseclass for statistical inefficiency
dnlbauer Aug 2, 2021
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
Prev Previous commit
Next Next commit
python 3 string formatting
@dnlbauer
dnlbauer committed Aug 2, 2021
commit 3b4cbe920f023a9091b16b85af6f27d8956e9dfb
7 changes: 4 additions & 3 deletions uncorrelate/statistical_inefficiency_dhdl.py
View file
Original file line number Diff line number Diff line change
@@ -54,17 +54,18 @@ def uncorrelate(self, dfs, lower):
dl.append(dli)

uncorrelated_dfs = []
print("Number of correlated and uncorrelated samples (Method=%s):\n\n%6s %12s %12s %12s\n" % ("dHdl", "State", "N", "N_k", "N/N_k"))
print("Number of correlated and uncorrelated samples (Method=dHdl (all)):")
print("\n State N N_k N/N_k\n")
for idx, (dhdl_, l, df) in enumerate(zip(self.dhdls, dl, dfs)):
ind = np.array(l, dtype=bool)
ind = np.array(ind, dtype=int)
dhdl_sum = dhdl_.dot(ind)
uncorrelated_df = alchemlyb.preprocessing.statistical_inefficiency(df, dhdl_sum, lower, conservative=False)
N, N_k = len(df), len(uncorrelated_df)
g = N/N_k
print("%6s %12s %12s %12.2f" % (idx, N, N_k, g))
print(f"{idx:>6} {N:>12} {N_k:>12} {g:>12.2f}")
if N_k < self.uncorr_threshold:
print("WARNING: Only %d uncorrelated samples found at lambda number %d; proceeding with analysis using correlated samples..." % (N_k, idx))
print(f"WARNING: Only {N_k} uncorrelated samples found at lambda number {idx}; proceeding with analysis using correlated samples...")
uncorrelated_dfs.append(df)
else:
uncorrelated_dfs.append(uncorrelated_df)
7 changes: 4 additions & 3 deletions uncorrelate/statistical_inefficiency_dhdl_all.py
View file
Original file line number Diff line number Diff line change
@@ -33,15 +33,16 @@ def uncorrelate(self, dfs, lower):
"""

uncorrelated_dfs = []
print("Number of correlated and uncorrelated samples (Method=%s):\n\n%6s %12s %12s %12s\n" % ("dHdl (all)", "State", "N", "N_k", "N/N_k"))
print("Number of correlated and uncorrelated samples (Method=dHdl (all)):")
print("\n State N N_k N/N_k\n")
for idx, (dhdl_, df) in enumerate(zip(self.dhdls, dfs)):
dhdl_sum = dhdl_.sum(axis=1)
uncorrelated_df = alchemlyb.preprocessing.statistical_inefficiency(df, dhdl_sum, lower, conservative=False)
N, N_k = len(df), len(uncorrelated_df)
g = N/N_k
print("%6s %12s %12s %12.2f" % (idx, N, N_k, g))
print(f"{idx:>6} {N:>12} {N_k:>12} {g:>12.2f}")
if N_k < self.uncorr_threshold:
print("WARNING: Only %d uncorrelated samples found at lambda number %d; proceeding with analysis using correlated samples..." % (N_k, idx))
print(f"WARNING: Only {N_k} uncorrelated samples found at lambda number {idx}; proceeding with analysis using correlated samples...")
uncorrelated_dfs.append(df)
else:
uncorrelated_dfs.append(uncorrelated_df)