reflexive 0.1.9__py3-none-any.whl → 1.0.14__py3-none-any.whl

reflexive/common/util.py

@@ -1,108 +0,0 @@
-
-# Utility functions
-from sklearn.preprocessing import MinMaxScaler
-
-class Util:
-    
-    def __init__(self):
-        self.name = "Util"
-
-    def sort_dict_by_value(self,d):
-        return dict(sorted(d.items(), key=lambda x:x[1], reverse=True))
-
-    def filter_dict_by_value(self,ngrams,min_val=3):
-        filtered_ngrams = {}
-        for k,v in ngrams.items():
-            if v >=min_val:
-                filtered_ngrams[k] = v
-        return filtered_ngrams
-
-    # Function to write dictionaries to both json and csv
-    def writeDictJsonCSV(self,dictionary,path_file):
-        with open(f"{path_file}.json",'w') as fp:
-            fp.write(json.dumps(dictionary))
-
-        ngram_df = pd.DataFrame.from_dict(dictionary,orient='index')   
-        ngram_df.to_csv(f"{path_file}.csv")
-
-    # Input a series and output a list of lists with each maxn elements
-    def series_to_chunked_list(self,series,maxn=25):
-        l = list(series)
-        return self.__chunk_list(l,maxn)
-    
-    # Chunk a list into a list of lists with maxn elements
-    def __chunk_list(self,l,maxn=25):
-        return [l[i:i + maxn] for i in range(0, len(l), maxn)]
-
-    # Count named entities
-    def count_entities(self,entities):
-        counts = []
-        for k,v in entities.items():
-            counts.append((k,len(v))) 
-        return sorted(counts, key=lambda x: x[1], reverse=True)
-    
-        # Function for calculating proportions of features
-    def ratios(self,elements):
-        etotal = sum([v[1] for v in elements])
-        if etotal==0:
-            return elements
-        else:
-            proportioned = []
-            for element in elements:
-                prop_val = round((element[1]/etotal),4)
-                proportioned.append((element[0],prop_val))
-            return proportioned
-
-
-    
-        # Count labels associated with strings
-    def count_labels(self,string_labels):
-        counts = dict()
-        for rt in string_labels:
-            counts[rt[1]] = counts.setdefault(rt[1],0) + 1
-        return sorted(counts.items(), key=lambda x: x[1], reverse=True)
-    
-    def count_keys(self,key_count_dict):
-        counts = dict()
-        for k,v in key_count_dict.items():
-            counts[k] = counts.setdefault(k,0) + v 
-        return sorted(counts.items(), key=lambda x: x[1], reverse=True)
-        
-     # Total the values in list of tuples
-    def tuple_values_total(self,tuples):
-        tvs = [t[1] for t in tuples]
-        return sum(tvs)
-
-#### SCALING AND NORMALISING
-
-    # Outliers
-
-    def outlier_fence(self,series):
-        bounds = {}
-        stats = series.describe()
-        iqr = stats['75%'] - stats['25%']
-        bounds["IQR"]=iqr
-        upper = stats['75%']+1.5*iqr
-        bounds["UPPER"]=upper
-        lower = stats['25%']-1.5*iqr
-        bounds["LOWER"]=lower
-        return bounds
-
-    # MinMax Scaling
-    def scale_min_max(self,df_cols):
-        scaler = MinMaxScaler()
-        return scaler.fit_transform(df_cols)
-
-    # Normalise domain term counts
-    def normalise_domain_counts(self,domain_counts,text_size):
-        norms = {}
-        for k,v in domain_counts.items():
-            norms[k] = round(v*text_size,3)
-        return norms
-
-    def normalise_scaled(self,df,feature,norm_feature = 'text_scaled'):
-        tempdf = df[[feature,norm_feature]].copy()
-        tempdf['norm_scaled'] = tempdf.apply(lambda r: round(r[feature]/(r[norm_feature]+0.01),4),axis=1)
-        return tempdf['norm_scaled']
-
-    

reflexive-0.1.9.dist-info/RECORD

@@ -1,20 +0,0 @@
-reflexive/__init__.py,sha256=DXmbgl_xMxd9Flqx3LXfbuYmYaJqzbDjB6r4mcPx75Y,292
-reflexive/analyse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-reflexive/analyse/aws_nlp.py,sha256=7uRZg4lRt6t33wAA-ZaKCWKWrA8aQJn31GwFpl8FWqQ,8355
-reflexive/analyse/general.py,sha256=ZPHkJcwwiV0CZQYa7JX9qjM5fm41MCPAq58GjtEtLKY,4388
-reflexive/analyse/reflexive_expressions.py,sha256=YGd346EH78KMOrzfAyP07o7DOvfQF9mybDSc4bZuoio,5121
-reflexive/aws_connect/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-reflexive/aws_connect/comprehend.py,sha256=eGbjf2Njy2KBTWd33GGrwFIk5e9GcKfUETBr_6mSvY0,7706
-reflexive/aws_connect/s3.py,sha256=l20haGTMmUPe_HjSi9jVu5oeyNC8VcVTD7X-CvDq1-o,3517
-reflexive/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-reflexive/common/local.py,sha256=euhMmdRnL5c5d_Co2f2ehNP7Lv43T571tDCWQzpKaF4,1752
-reflexive/common/parameters.py,sha256=o0Yw3dvSdVvEC46Q1a_QK0mr7uDIb_SCmUYWUyspSM0,3305
-reflexive/common/util.py,sha256=OIfdQpkg3WLz0Ymm3OYlvOEE_ZGlI4KQHc8PYPb4vn8,3458
-reflexive/visual/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-reflexive/visual/display.py,sha256=XiRC3Asx9Ed3xCNCt3_DlbF45JcifNbXH_B44jxqqp0,3886
-reflexive-0.1.9.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-reflexive-0.1.9.dist-info/LICENSE.txt,sha256=WNHhf_5RCaeuKWyq_K39vmp9F28LxKsB4SpomwSZ2L0,11357
-reflexive-0.1.9.dist-info/METADATA,sha256=2y2QHK_2H-b3jXDbsgfl07pPxtLjPtU_fyDkpRrv-98,12037
-reflexive-0.1.9.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-reflexive-0.1.9.dist-info/top_level.txt,sha256=pOMr-QGleRBRCFBozgvM-UUUmOjD_-naJfu1522E2V8,10
-reflexive-0.1.9.dist-info/RECORD,,