notebook.community

Edit and run 





In [1]:



    


# written in python3
import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import os
from datetime import datetime
import seaborn as sns
%matplotlib inline
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import FeatureUnion
from sklearn.preprocessing import PolynomialFeatures
from sklearn.metrics import confusion_matrix
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.linear_model import LinearRegression

class DataFrameSelector(BaseEstimator, TransformerMixin):
    def __init__(self, attribute_names):
        self.attribute_names = attribute_names
    def fit(self, X, y=None):
        return self
    def transform(self, X):
        return X[self.attribute_names].values
    
plt.rcParams['figure.figsize'] = (10,6.180)    #golden ratio


def my_transform(data, label, degree, FEATURES):

    # LABEL = "Qw"
    LABEL = label
    PolynomialDegree = degree

    num_attribs = FEATURES
    cat_attribs = [LABEL]
    num_pipeline = Pipeline([
            ('selector', DataFrameSelector(num_attribs)),
            ('std_scaler', StandardScaler()),
            ('poly', PolynomialFeatures(degree=PolynomialDegree, include_bias=False))
        ])
    cat_pipeline = Pipeline([
            ('selector', DataFrameSelector(cat_attribs))
        ])

    full_pipeline = FeatureUnion(transformer_list=[
            ("num_pipeline", num_pipeline),
            ("cat_pipeline", cat_pipeline),
        ])
    return full_pipeline.fit_transform(data)

functions for reading data





In [2]:



    


# read energy, rw, bias, rmsd data from location
def read_data(name):
#     name="tr872"
    name_list = ["Step" , "Chain" , "Shake" , "Chi" , "Rama", "Excluded", "DSSP", "P_AP", "Water" ,"Burial", "Helix", "AMH_Go", "Frag_Mem", "Vec_FM", "Membrane", "SSB","VTotal"]

    # you probably want to change the location below
#     location = f"/Users/weilu/Research/server/sep_2018/03_week/02_week/{name}/"
    location = f"/Users/weilu/Research/server/oct_2018/01_week/{name}/"
    RMSD = pd.read_table(location+"rmsd-angstrom.xvg", names=["i", "RMSD"], sep="\s+")
    bias = pd.read_table(location+"bias.log", names=["i", "biasQ", "bias"], sep="\s+").drop("i", axis=1)
    awsem = pd.read_table(location+"awsem.log", names=name_list)
    rw = pd.read_table(location+"rwplusScore.txt", names=["i", "Rw"], sep="\s+").drop("i", axis=1)
    # pc location
    location = f"/Users/weilu/Research/server/sep_2018/03_week/{name}/"
    location = f"/Users/weilu/Research/server/oct_2018/01_week/{name}/"
    pc = pd.read_table(location+"pcarmsd_scaled.txt", names=["i", "pc", "pc2"], sep="\s+").drop("i", axis=1)
    raw_data = pd.concat([RMSD, rw, bias, awsem, pc], axis=1)
    return raw_data.assign(name=name).reset_index().rename(columns={"index":"folder"})

def choose_top(data,col="RMSD", n=5, ascending=True):
    return data.assign(chosen=pd.DataFrame.rank(data[col], ascending=ascending, method='dense')<=n)

# read the pmf, rc. 
def read_data_2(name):
#     name = "tr894"
    location = f"/Users/weilu/Research/server/sep_2018/03_week/{name}/"
    location = f"/Users/weilu/Research/server/oct_2018/01_week/{name}/"
    rw = pd.read_table(location+"rc_rwplus", names=["pc","rw"], sep="\s+")
    rmsd = pd.read_table(location+"rc_rmsdlowerBound", names=["pc", "rmsd"], sep="\s+")
    awsem = pd.read_table(location+"rc_awsemEne", names=["pc", "awsem"], sep="\s+")
    freeE = pd.read_table(location+"pmf3000"
                          , names=["pc", "f", "remove1", "remove2"], sep="\s+").drop(["remove1", "remove2"], axis=1)
    raw_data = freeE.merge(rw, on="pc").merge(awsem, on="pc").merge(rmsd, on="pc").assign(name=name)
    return raw_data

train based on free energy, rw and awsem.





In [35]:



    


# folder_list = ["tr894", "tr882", "tr594", "tr898", "tr862", "tr877", "tr872", "tr885", "tr866", "tr868", "tr884", "tr895", "tr896", "tr870", "tr921", "tr922", "tr891", "tr948"]
folder_list = ["tr894", "tr882", "tr594", "tr869", "tr862", "tr877", "tr872", "tr885", "tr866", "tr868", "tr884", "tr895", "tr896", "tr870", "tr921", "tr922", "tr891", "tr948"]
# folder_list = [ "tr862", "tr877", "tr872", "tr885", "tr866", "tr868", "tr884", "tr895", "tr896", "tr870", "tr921", "tr922", "tr891", "tr948"]
# folder_list = ["tr862", "tr872", "tr885", "tr866", "tr868" , "tr895", "tr896", "tr870", "tr921", "tr891", "tr948"]
# "tr877","tr884", "tr922"
# "tr869"
# folder_list = ["tr894"]
# read all data
data_list = []
for name in folder_list:
    tmp = read_data_2(name)
    data_list.append(tmp)
raw_data_all = pd.concat(data_list)
n = 1
raw_data_all = raw_data_all.reset_index(drop=True).groupby("name").apply(choose_top, n=n, col="rmsd").reset_index(drop=True)


# train_name_list = ["tr872", "tr885", "tr948"]
# train_name_list = ["tr862", "tr872", "tr885", "tr866", "tr868" , "tr895", "tr896", "tr870", "tr921", "tr891", "tr948"]
# train_name_list = ["tr866", "tr866"]
# train_name_list = ["tr870"]
# train_name_list = ["tr891"]
train_name_list = ["tr882"]
train_name_list = ["tr894"]
train_name_list = ["tr872"]
# select for training.
raw_data = raw_data_all.reset_index(drop=True).query(f'name in {train_name_list}')



    


















    






/Users/weilu/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:13: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version
of pandas will change to not sort by default.

To accept the future behavior, pass 'sort=False'.

To retain the current behavior and silence the warning, pass 'sort=True'.

  del sys.path[0]

















In [36]:



    


# FEATURES = ["eigenvalues", "entropy", "pca"]
# FEATURES = ["eigenvalues", "entropy", "diffRMSD"]
# FEATURES = ["eigenvalues", "entropy"]
FEATURES = ["f",
    'rw',
     'awsem',
#     'RMSD', # test
#      'Burial',
#      'Water',
#      'Rama',
#      'DSSP',
#      'P_AP',
#      'Helix',
#      'Frag_Mem'
               ]
# FEATURES = ["eigenvalues"]
# LABEL = "diffRMSD"
# LABEL = "RMSD"
LABEL = "rmsd"
DEGREE = 1

def pred_from_raw(a):
    data = my_transform(a, label=LABEL, degree=DEGREE, FEATURES=FEATURES)
    test_y = data[:,-1]
    test_set = data[:,:-1]
    prediceted_rmsd= clf.predict(test_set)
    return a.assign(prediceted_rmsd=prediceted_rmsd)



    











In [37]:



    


# data = my_transform(raw_data, label=LABEL, degree=DEGREE, FEATURES=FEATURES)
# data = raw_data.groupby('name').apply(my_transform, label=LABEL, degree=DEGREE, FEATURES=FEATURES)[0]
data = np.concatenate(raw_data.groupby('name').apply(my_transform, 
                                                     label=LABEL, degree=DEGREE, FEATURES=FEATURES).values)
train_y = data[:,-1]
train_set = data[:,:-1]
from sklearn import svm
# clf = svm.SVC(probability=True)
clf = LinearRegression()
clf.fit(train_set, train_y)
y_pred_svm = clf.predict(train_set)

raw_data_all = raw_data_all.reset_index(drop=True).groupby("name").apply(pred_from_raw).reset_index(drop=True)


picked_n = 1
best = raw_data_all.groupby("name").apply(choose_top, col="rmsd"
                                            , n=picked_n, ascending=True).reset_index(drop=True).query("chosen==True")
picked = raw_data_all.groupby("name").apply(choose_top, col="prediceted_rmsd"
                                            , n=picked_n, ascending=True).reset_index(drop=True).query("chosen==True")
# init = raw_data_all.query("i == 0.0")
all_results = pd.concat([best.assign(result='best'), 
                         picked.assign(result='picked')])

picked_keep = picked.copy()



    











In [38]:



    


picked_keep



    


















    
Out[38]:











  
    

      
      awsem
      f
      name
      pc
      rmsd
      rw
      chosen
      prediceted_rmsd
    

  
  
    

      14
      -880.678333
      0.463528
      tr594
      0.703
      0.664941
      -9183.746000
      True
      0.334709
    

    

      30
      -1399.267143
      0.157757
      tr862
      0.778
      0.597626
      -13495.805143
      True
      0.398927
    

    

      40
      -1720.443376
      0.135796
      tr868
      -0.065
      0.227528
      -17892.774089
      True
      0.314273
    

    

      57
      -1076.527368
      0.000000
      tr872
      -0.386
      0.353299
      -12231.207105
      True
      0.357682
    

    

      78
      -1586.793591
      3.999900
      tr877
      0.548
      0.405186
      -22994.153348
      True
      0.354661
    

    

      87
      -1075.864409
      0.506056
      tr882
      -0.653
      0.216262
      -11925.295597
      True
      0.359481
    

    

      101
      -847.801778
      1.892033
      tr884
      -3.050
      0.568444
      -8835.388444
      True
      0.362636
    

    

      147
      -1632.289710
      3.429739
      tr885
      0.327
      0.232037
      -19318.358551
      True
      0.357051
    

    

      193
      -1537.503333
      1.739592
      tr891
      3.560
      0.329000
      -17639.060000
      True
      0.310352
    

    

      215
      -609.629731
      0.132114
      tr894
      0.430
      0.296858
      -6518.979065
      True
      0.350120
    

    

      229
      -1591.930000
      0.000000
      tr895
      -1.105
      0.473486
      -20400.668442
      True
      0.362495
    

    

      249
      -878.581472
      0.000000
      tr896
      -0.580
      0.834744
      -10854.022546
      True
      0.313762
    

    

      263
      -2639.662051
      2.569714
      tr921
      -2.344
      0.386769
      -20902.350256
      True
      0.316512
    

    

      299
      -899.214063
      1.005065
      tr922
      0.341
      0.508805
      -9011.376508
      True
      0.367383
    

    

      337
      -2453.823333
      1.734273
      tr948
      2.794
      0.760035
      -27470.107000
      True
      0.332109

used picked_keep as to filter the compelete data and select again





In [39]:



    


def choose_top(data,col="RMSD", n=5, ascending=True):
    return data.assign(chosen=pd.DataFrame.rank(data[col], ascending=ascending, method='first')<=n)


WIDTH = 100
# WIDTH = 1
def with_in_range(data, width=WIDTH):
    return data.assign(inrange= (data["pc"] < (data["pc_center"]+width)) & (data["pc"] > (data["pc_center"]-width)))



    











In [42]:



    


folder_list = ["tr894", "tr882", "tr594", "tr862", "tr877", "tr872", "tr885", "tr866", "tr868", "tr884", "tr895", "tr896", "tr870", "tr921", "tr922", "tr891", "tr948"]
# "tr898"
# folder_list = ["tr894", "tr882", "tr594", "tr898", "tr862", "tr877", "tr872", "tr885", "tr866", "tr868", "tr884", "tr895", "tr896", "tr870", "tr921", "tr922", "tr891", "tr948"]
# folder_list = ["tr894", "tr882", "tr594", "tr869", "tr862", "tr877", "tr872", "tr885", "tr866", "tr868", "tr884", "tr895", "tr896", "tr870", "tr921", "tr922", "tr891", "tr948"]
# folder_list = [ "tr862", "tr877", "tr872", "tr885", "tr866", "tr868", "tr884", "tr895", "tr896", "tr870", "tr921", "tr922", "tr891", "tr948"]
# folder_list = ["tr862", "tr872", "tr885", "tr866", "tr868" , "tr895", "tr896", "tr870", "tr921", "tr891", "tr948"]
# "tr877","tr884", "tr922"
# "tr869"
# folder_list = ["tr894"]
data_list = []
for name in folder_list:
    tmp = read_data(name)
    data_list.append(tmp)
raw_data_all_2 = pd.concat(data_list).dropna()
n = 10
raw_data_all_2 = raw_data_all_2.reset_index(drop=True).groupby("name").apply(choose_top, n=n, col="RMSD").reset_index(drop=True)


raw_data = raw_data_all_2.reset_index(drop=True).query(f'name in {train_name_list}').dropna()
a = raw_data_all_2.dropna().merge(picked_keep[["pc", "name"]].rename(columns={"pc":"pc_center"}),on="name")
filtered = a.groupby("name").apply(with_in_range).query("inrange == True").reset_index(drop=True)



    











In [43]:



    


# FEATURES = ["eigenvalues", "entropy", "pca"]
# FEATURES = ["eigenvalues", "entropy", "diffRMSD"]
# FEATURES = ["eigenvalues", "entropy"]
FEATURES = [
    "biasQ",
    'Rw',
     'VTotal',
#     'RMSD', # test
#      'Burial',
#      'Water',
#      'Rama',
#      'DSSP',
#      'P_AP',
#      'Helix',
#      'Frag_Mem'
               ]
# FEATURES = ["eigenvalues"]
# LABEL = "diffRMSD"
# LABEL = "RMSD"
LABEL = "chosen"
DEGREE = 1

def pred_from_raw(a):
    data = my_transform(a, label=LABEL, degree=DEGREE, FEATURES=FEATURES)
    test_y = data[:,-1]
    test_set = data[:,:-1]
    prob= clf.predict_proba(test_set)[:,1]
    return a.assign(prob=prob)

# data = my_transform(raw_data, label=LABEL, degree=DEGREE, FEATURES=FEATURES)
# data = raw_data.groupby('name').apply(my_transform, label=LABEL, degree=DEGREE, FEATURES=FEATURES)[0]
data = np.concatenate(raw_data.groupby('name').apply(my_transform, 
                                                     label=LABEL, degree=DEGREE, FEATURES=FEATURES).values)
train_y = data[:,-1]
train_set = data[:,:-1]

# clf = svm.SVC(probability=True)
p = 0.01
# clf = LogisticRegression(random_state=27, class_weight={0:p, 1:(1-p)})
clf = LogisticRegression(random_state=27)
clf.fit(train_set, train_y)

filtered = filtered.reset_index(drop=True).groupby("name").apply(pred_from_raw).reset_index(drop=True)


picked_n = 1
best = raw_data_all_2.groupby("name").apply(choose_top, col="RMSD"
                                            , n=1, ascending=True).reset_index(drop=True).query("chosen==True")
picked = filtered.groupby("name").apply(choose_top, col="prob"
                                            , n=1, ascending=False).reset_index(drop=True).query("chosen==True")
worst = filtered.groupby("name").apply(choose_top, col="RMSD"
                                            , n=1, ascending=False).reset_index(drop=True).query("chosen==True")
init = raw_data_all_2.groupby("name").apply(choose_top, col="i"
                                            , n=1, ascending=True).reset_index(drop=True).query("chosen==True")
all_results = pd.concat([best.assign(result='best'), 
                         picked.assign(result='picked'), init.assign(result='init')
#                         , worst.assign(result='worst')
                        ], sort=False)
# all_results = pd.concat([best.assign(result='best'), 
#                          picked.assign(result='picked')])
# picked.to_csv("/Users/weilu/Desktop/picked.csv

# sns.set(rc={'figure.figsize':(20,30)})
# plt.figure(figsize=(15,8))
fg = sns.FacetGrid(data=all_results.reset_index(), hue='result', height=8, aspect=1.63)
fg.map(plt.plot, 'name', 'RMSD').add_legend(fontsize=20)
fg.set(ylim=(0, 10))



    


















    






/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)
/Users/weilu/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:475: DataConversionWarning: Data with input dtype object was converted to float64 by StandardScaler.
  warnings.warn(msg, DataConversionWarning)










    
Out[43]:








<seaborn.axisgrid.FacetGrid at 0x1a22f2b860>










    
























In [23]:



    


picked["init_RMSD"] = init["RMSD"].values
picked["diff_RMSD"] = init["RMSD"].values - picked["RMSD"].values
out = picked[["name", "RMSD", "init_RMSD", "diff_RMSD", "folder"]].reset_index(drop=True)



    











In [24]:



    


filtered.plot.scatter("prob", "RMSD")



    


















    
Out[24]:








<matplotlib.axes._subplots.AxesSubplot at 0x1a238633c8>










    
























In [25]:



    


out



    


















    
Out[25]:











  
    

      
      name
      RMSD
      init_RMSD
      diff_RMSD
      folder
    

  
  
    

      0
      tr894
      1.36968
      2.24606
      0.87638
      980
    

  




















In [13]:



    


raw_data_all_2.plot("RMSD", "Rw")



    


















    
Out[13]:








<matplotlib.axes._subplots.AxesSubplot at 0x1a23707f60>










    
























In [14]:



    


raw_data_all_2.plot("RMSD", "pc")



    


















    
Out[14]:








<matplotlib.axes._subplots.AxesSubplot at 0x1a23783828>










    
























In [15]:



    


out



    


















    
Out[15]:











  
    

      
      name
      RMSD
      init_RMSD
      diff_RMSD
      folder
    

  
  
    

      0
      tr894
      1.36968
      2.24606
      0.87638
      980
    

  




















In [16]:



    


out



    


















    
Out[16]:











  
    

      
      name
      RMSD
      init_RMSD
      diff_RMSD
      folder
    

  
  
    

      0
      tr894
      1.36968
      2.24606
      0.87638
      980
    

  




















In [70]:



    


all_results



    


















    
Out[70]:











  
    

      
      folder
      i
      RMSD
      Rw
      biasQ
      bias
      Step
      Chain
      Shake
      Chi
      ...
      SSB
      VTotal
      pc
      pc2
      name
      chosen
      result
      pc_center
      inrange
      prob
    

  
  
    

      980
      980
      47900.0
      1.36968
      -6834.949362
      0.645772
      25.095468
      0
      3.685220
      0.0
      0.588609
      ...
      0.0
      -656.184416
      0.944122
      -0.804111
      tr894
      True
      best
      NaN
      NaN
      NaN
    

    

      981
      981
      48000.0
      1.57229
      -6850.297788
      0.673878
      21.271087
      0
      4.750551
      0.0
      0.512601
      ...
      0.0
      -659.909501
      0.762314
      -0.531746
      tr894
      True
      picked
      2.03
      True
      0.523816
    

    

      0
      0
      0.0
      2.24606
      -6810.073249
      0.556208
      39.390241
      0
      5.546380
      0.0
      1.160888
      ...
      0.0
      -668.558313
      -0.065067
      -0.283718
      tr894
      True
      init
      NaN
      NaN
      NaN
    

  



3 rows × 31 columns



















In [13]:



    


# out.to_csv("/Users/weilu/Desktop/picked_3.csv")



    











In [26]:



    


clf.coef_



    


















    
Out[26]:








array([[ 0.31865771, -0.24574338, -0.00429271, -0.15621297,  0.12086065,
         0.03529636,  0.05114406,  0.06779384,  0.23049113, -0.0941187 ]])

















In [14]:



    


clf.coef_



    


















    
Out[14]:








array([[ 0.20157408, -0.69485223,  0.04456798]])

















In [15]:



    


fg = sns.FacetGrid(data=all_results.reset_index(), hue='result', height=8, aspect=1.63)
fg.map(plt.plot, 'name', 'RMSD').add_legend(fontsize=20)
fg.set(ylim=(0, 10))



    


















    
Out[15]:








<seaborn.axisgrid.FacetGrid at 0x1a22576f60>










    
























In [16]:



    


filtered["name"].unique().shape



    


















    
Out[16]:








(17,)

















In [17]:



    


picked[["RMSD", "name"]]



    


















    
Out[17]:











  
    

      
      RMSD
      name
    

  
  
    

      0
      5.14331
      tr594
    

    

      1136
      4.31091
      tr862
    

    

      1890
      3.14792
      tr866
    

    

      2586
      1.61058
      tr868
    

    

      3123
      8.69691
      tr870
    

    

      3576
      2.81351
      tr872
    

    

      4796
      3.07719
      tr877
    

    

      5446
      2.25775
      tr882
    

    

      6372
      4.06919
      tr884
    

    

      6989
      2.35937
      tr885
    

    

      7922
      1.60893
      tr891
    

    

      9265
      1.18208
      tr894
    

    

      10424
      4.67184
      tr895
    

    

      10781
      8.22359
      tr896
    

    

      14297
      3.25991
      tr921
    

    

      14558
      3.84193
      tr922
    

    

      16140
      5.40097
      tr948
    

  




















In [18]:



    


# picked.to_csv("/Users/weilu/Desktop/picked_2.csv")



    











In [ ]:

Content source: luwei0917/awsemmd_script

Similar notebooks:

notebook.community | gallery | about