levin
/
source_code_classification
mirror of https://github.com/whatevernevermindbro/source_code_classification


  
1

	
2

	
3

	
4

	
5

	
6

	
7

	
8

	
9

	
10

	
11

	
12

	
13

	
14

	
15

	
16

	
17

	
18

	
19

	
20

	
21

	
22

	
23

	
24

	
25

	
26

	
27

	
28

	
29

	
30

	
31

	
32

	
33

	
34

	
35

	
36

	
37

	
38

	
39

	
40

	
41

	
42

	
            {
	"imports": ["import", "from"],

   	"data_load": [".load", "_load", "_dump", "load_", ".csv", "glob", "pickle.", "read_", "download", ".txt", ".json", ".png", ".jpg", ".jpeg"],

	"preprocessing": ["train_test_split(", "Normalizer(", "StandardScaler(", "normalize(", "scale(", "DictVectorizer(", 
					"CountVectorizer(", "HashingVectorizer(", "TfidfVectorizer(", "Stemmer(",
					"Lemmatizer(", "convert", ".resize", "encode(", ".fill(", ".fillna(",
					".concat(", ".concat (",  ".concatenate(", ".concatenate (", "merge",
					"train_test_split (", "Normalizer (", "StandardScaler (", "normalize (",
					"scale (","DictVectorizer (", "CountVectorizer (", "HashingVectorizer (",
					"TfidfVectorizer (", "Stemmer (", "Lemmatizer (", "encode (", ".fill (",
					".fillna (", "preprocess", "generation", "augmentation", "stemming",
					"lemmatization", "scale", ".normalize", ".crop", "crop(", "crop (", "resize(",
					"resize (", "invert_xaxis", "print_results", "attention", ".drop(", ".drop (",
					"preprocessing", "test_size", "test_split", "font_scale", "scale", "color_contonuous_scale",
					"colorscale", "encode", "preprocessor", "set_vscale", "rescale", "reversescale",
					"inverse_transform", "porterstemmer", "stem", "simple_preprocess",
					"ploynomialfeatures", "autoscale", "lemmatize", "lemmatizer", "pd_merge_all",
					"stemmer", "labelencoder", "LabelEncoder", "minmaxscaler", "converted",
					"preprocess_image", "vectorizer", "tokenizer", "tfidf", "stemmer", "scaled_train",
					"input_ids", "combined_merged", "pucountry_convert", "stemming", "replace", "lambda",
					"map(", "filter(", ".get_dummies", ".fit_transform", ".transform", ".strip", ".split",
					".apply", ".dropna", "clean", "duplicated", "drop_duplicated", "decode", "reshape",
					"deskew", ".str.contains", "iaa.", "augmentation", "A.", "flatten", ".groupby",
					".sort_values", ".pad", "prepare", "pivot", ".melt", "rotate", "re.", "sorted(",
					".reset_index("
					],

    "visualization": ["plotting", "plot.", "plt.", "graph", "histogram", "hist", "sns.", "plotline", "chart", "diagram", "heatmap", "figure", "plot_tree(", "plot_tree (", "boxplot"],

    "model": ["LinearRegression(", "RandomForest(", "Ridge(", "RidgeCV(", "RidgeClassifier(", "RidgeClassifierCV(", "Lasso(", "SGD(", "LogisticRegression(", "LogisticRegressionCV(", "SVC(", "SVR(",
		"Layer(", "XGboost(", "LGBM(", "CatBoost(", "Perceptron(", "KNeighborsRegressor(", "KNeighborsClassifier(", "SGDRegressor(", "ElasticNet(", "ElasticNetCV(", "KMeans(",
		"AgglomerativeClustering(", "SpectralClustering(", "CategoricalNB(", "ComplementNB(", "DecisionTreeClassifier(", "DecisionTreeRegressor(", "LinearRegression (", "RandomForest (",
		"Ridge (", "RidgeCV (", "RidgeClassifier (", "RidgeClassifierCV (", "Lasso (", "SGD (", "LogisticRegression (", "LogisticRegressionCV (", "SVC (", "SVR (", "Layer (", "XGboost (",
		"LGBM (", "CatBoost (", "Perceptron (", "KNeighborsRegressor (", "KNeighborsClassifier (", "SGDRegressor (", "ElasticNet (", "ElasticNetCV (", "KMeans (", "AgglomerativeClustering (",
		"SpectralClustering (", "CategoricalNB (", "ComplementNB (", "DecisionTreeClassifier (", "DecisionTreeRegressor ("],

    "train": [".fit", "epoch", "loss", "optimizer"],

    "predict": [".predict", "_error", ".mean_", "_score", "_distance"]
}