Merge pull request #2068 from NNPDF/fix_ct_docs

update the closure test docs

doc/sphinx/source/tutorials/closuretest.md

@@ -55,12 +55,7 @@ closuretest:
   filterseed  : 0   # Random seed to be used in filtering data partitions
   fakedata    : False
   fakepdf     : MMHT2014nnlo68cl
-  errorsize   : 1.0 # uncertainties rescaling
   fakenoise   : False
-  rancutprob  : 1.0 # Fraction of data to be included in the fit
-  rancutmethod: 0   # Method to select rancutprob data fraction
-  rancuttrnval: False # 0(1) to output training(valiation) chi2 in report
-  printpdf4gen: False # To print info on PDFs during minimization
 ```
 
 Setting ``fakedata`` to ``True`` will cause closure test pseudodata to be generated
@@ -80,21 +75,15 @@ closuretest:
   filterseed  : 0   # Random seed to be used in filtering data partitions
   fakedata    : True
   fakepdf     : MMHT2014nnlo68cl
-  errorsize   : 1.0 # uncertainties rescaling
   fakenoise   : True
-  rancutprob  : 1.0 # Fraction of data to be included in the fit
-  rancutmethod: 0   # Method to select rancutprob data fraction
-  rancuttrnval: False # 0(1) to output training(valiation) chi2 in report
-  printpdf4gen: False # To print info on PDFs during minimization
 ```
 Note that it is *critical* that two closure tests which are to be compared have
 the same ``filterseed``. They should also both have been run during a time where
 no major changes were made to data generation. This is because fits with
 different level 1 noise produce different closure test estimators. See for
 example a [report](https://vp.nnpdf.science/mbcTUd6-TQmQFvaGd37bkg==/)
 comparing two level 2 closure tests with identical settings apart from
-``filterseed``. Note that setting ``filterseed`` to 0 will use the default seed for
-the selected ``fitting::rngalgo``.
+``filterseed``.
 
 There are still some relevant settings to the closure test. For the above example
 we would choose that the t0 set was the same as the underlying law:

n3fit/runcards/examples/Basic_runcard_closure_test.yml

@@ -0,0 +1,88 @@
+#
+# Configuration file for n3fit
+#
+############################################################
+description: Basic closure test runcard
+
+############################################################
+# frac: training fraction
+# ewk: apply ewk k-factors
+# sys: systematics treatment (see systypes)
+dataset_inputs:
+- {dataset: NMC_NC_NOTFIXED_DW_EM-F2, frac: 0.75, variant: legacy}
+- {dataset: SLAC_NC_NOTFIXED_D_DW_EM-F2, frac: 0.75, variant: legacy}
+- {dataset: ATLAS_Z0J_8TEV_PT-M, frac: 0.75, cfac: [], variant: legacy_10}
+
+############################################################
+datacuts:
+  t0pdfset     : NNPDF40_nnlo_as_01180 # PDF set to generate t0 covmat
+  q2min        : 3.49                # Q2 minimum
+  w2min        : 12.5                # W2 minimum
+
+############################################################
+theory:
+  theoryid: 708       # database id
+
+sampling:
+  separate_multiplicative: true
+parameters: # This defines the parameter dictionary that is passed to the Model Trainer
+  nodes_per_layer: [15, 10, 8]
+  activation_per_layer: ['sigmoid', 'sigmoid', 'linear']
+  initializer: 'glorot_normal'
+  optimizer:
+    optimizer_name: 'RMSprop'
+    learning_rate: 0.01
+    clipnorm: 1.0
+  epochs: 900
+  positivity:
+    multiplier: 1.05 # When any of the multiplier and/or the initial is not set
+    initial: # the maxlambda will be used instead to compute these values per dataset
+    threshold: 1e-5
+  stopping_patience: 0.30 # percentage of the number of epochs
+  layer_type: 'dense'
+  dropout: 0.0
+  threshold_chi2: 5.0
+
+############################################################
+trvlseed: 1
+nnseed: 2
+mcseed: 3
+genrep: True     # true = generate MC replicas, false = use real data
+
+fitting:
+  # NN23(QED) = sng=0,g=1,v=2,t3=3,ds=4,sp=5,sm=6,(pht=7)
+  # EVOL(QED) = sng=0,g=1,v=2,v3=3,v8=4,t3=5,t8=6,(pht=7)
+  # EVOLS(QED)= sng=0,g=1,v=2,v8=4,t3=4,t8=5,ds=6,(pht=7)
+  # FLVR(QED) = g=0, u=1, ubar=2, d=3, dbar=4, s=5, sbar=6, (pht=7)
+  fitbasis: NN31IC # EVOL (7), EVOLQED (8), etc.
+  basis:
+      # remeber to change the name of PDF accordingly with fitbasis
+      - { fl: sng,  smallx: [1.05,1.19], largex: [1.47,2.70], trainable: False }
+      - { fl: g,    smallx: [0.94,1.25], largex: [0.11,5.87], trainable: False }
+      - { fl: v,    smallx: [0.54,0.75], largex: [1.15,2.76], trainable: False }
+      - { fl: v3,   smallx: [0.21,0.57], largex: [1.35,3.08] }
+      - { fl: v8,   smallx: [0.52,0.76], largex: [0.77,3.56], trainable: True }
+      - { fl: t3,   smallx: [-0.37,1.52], largex: [1.74,3.39] }
+      - { fl: t8,   smallx: [0.56,1.29], largex: [1.45,3.03] }
+      - { fl: cp,   smallx: [0.12,1.19], largex: [1.83,6.70] }
+
+############################################################
+positivity:
+  posdatasets:
+  - {dataset: NNPDF_POS_2P24GEV_F2U, maxlambda: 1e6}        # Positivity Lagrange Multiplier
+  - {dataset: NNPDF_POS_2P24GEV_FLL-19PTS, maxlambda: 1e6}
+
+############################################################
+integrability:
+  integdatasets:
+  - {dataset: NNPDF_INTEG_3GEV_XT3, maxlambda: 1e2}
+
+############################################################
+debug: True
+maxcores: 8
+
+closuretest:
+  filterseed: 3345348918 # Random seed to be used in filtering data partitions
+  fakedata: true     # true = to use FAKEPDF to generate pseudo-data
+  fakepdf: NNPDF40_nnlo_as_01180      # Theory input for pseudo-data
+  fakenoise: true    # true = to add random fluctuations to pseudo-data