edson-github · sourcery-ai · May 4, 2023 · sourcery-ai · May 4, 2023 · sourcery-ai
diff --git a/Deployment/Linear_regression/request_pred.py b/Deployment/Linear_regression/request_pred.py
@@ -27,11 +27,11 @@
 if (str(resp.status_code)=='200'):
 	print("Response received correctly.")
 	print()
-	
+
 x=resp.json()
 j = json.loads(x)
 d = dict(j)
 
 for k,v in (d.items()):
-	print("{}: {}".format(k,round(v,2)))
+	print(f"{k}: {round(v, 2)}")
 	print()
diff --git a/Deployment/Linear_regression/server_lm.py b/Deployment/Linear_regression/server_lm.py
@@ -21,25 +21,24 @@ def apicall():
 	except Exception as e:
 		raise e
 
-	clf = 'lm_model_v1.pk'
-
 	if test.empty:
 		return(bad_request())
-	else:
-		#Load the saved model
-		print("Loading the model...")
-		loaded_model = None
-		with open('./models/'+clf,'rb') as f:
-			loaded_model = pickle.load(f)
-
-		print("The model has been loaded...doing predictions now...")
-		print()
-		predictions = loaded_model.predict(test)
-
-		prediction_series = pd.Series(predictions)
-		response = jsonify(prediction_series.to_json())
-		response.status_code = 200
-		return (response)
+	#Load the saved model
+	print("Loading the model...")
+	loaded_model = None
+	clf = 'lm_model_v1.pk'
+
+	with open(f'./models/{clf}', 'rb') as f:
+		loaded_model = pickle.load(f)
+
+	print("The model has been loaded...doing predictions now...")
+	print()
+	predictions = loaded_model.predict(test)
+
+	prediction_series = pd.Series(predictions)
+	response = jsonify(prediction_series.to_json())
+	response.status_code = 200
+	return (response)
 
 @app.errorhandler(400)
 def bad_request(error=None):

diff --git a/Deployment/Linear_regression/training_housing.py b/Deployment/Linear_regression/training_housing.py
@@ -1,7 +1,7 @@
 import numpy as np
 import pandas as pd
 
-import os 
+import os
 import json
 import io
 import requests
@@ -17,36 +17,36 @@
 
 # Checks if the dataset is in the local '/data' folder
 # If not present, pulls from Github repo, otherwise reads from the local folder
-if not os.path.isdir(cwd+"/data") or data_filename not in os.listdir(cwd+"/data"):
+if not os.path.isdir(f"{cwd}/data") or data_filename not in os.listdir(
+	f"{cwd}/data"
+):
 	url="https://raw.githubusercontent.com/tirthajyoti/Machine-Learning-with-Python/master/Datasets/USA_Housing.csv"
-	print("Downloading data from {} ".format(url))
+	print(f"Downloading data from {url} ")
 	s=requests.get(url).content
 
 	df = pd.read_csv(io.StringIO(s.decode('utf-8')))
 	print("Dataset is downloaded.")
 	# Save the data in local '/data' folder
-	if not os.path.isdir(cwd+"/data"):
-		os.makedirs(cwd+"/data")
+	if not os.path.isdir(f"{cwd}/data"):
+		os.makedirs(f"{cwd}/data")
 	df.to_csv("data/USA_housing.csv")
-	print()
 else:
 	df = pd.read_csv("data/USA_housing.csv")
 	print("Dataset loaded from local directory")
-	print()
-
+print()
 # Make a list of data frame column names
 l_column = list(df.columns) # Making a list out of column names
 len_feature = len(l_column) # Length of column vector list
 
 # Put all the numerical features in X and Price in y, 
 # Ignore Address which is string for linear regression
-X = df[l_column[0:len_feature-2]]
+X = df[l_column[:len_feature-2]]
 y = df[l_column[len_feature-2]]
 
 #print("Feature set size:",X.shape)
 #print("Variable set size:",y.shape)
 #print()
-print("Features variables: ",l_column[0:len_feature-2])
+print("Features variables: ", l_column[:len_feature-2])
 print()
 
 # Create X and y train and test splits in one command using a split ratio and a random seed
@@ -83,16 +83,14 @@
 if __name__ == '__main__':
 	filename = 'lm_model_v1.pk'
 	print("Now saving the model to a serialized format (pickle)...")
-	if not os.path.isdir(cwd+"/models"):
+	if not os.path.isdir(f"{cwd}/models"):
 		os.makedirs(cwd+"/models")
 	with open('models/'+filename, 'wb') as file:
 		pickle.dump(lm, file)
 	# Save some of the test data in a CSV
 	print("Saving test data to a file...")
 	print()
-	if os.path.isdir(cwd+"/data"):
-		X_test.to_csv("data/housing_test.csv")
-	else:
+	if not os.path.isdir(cwd + "/data"):
 		os.makedirs(cwd+"/data")
-		X_test.to_csv("data/housing_test.csv")
+	X_test.to_csv("data/housing_test.csv")
 
diff --git a/Deployment/rnn_app/utils.py b/Deployment/rnn_app/utils.py
@@ -32,8 +32,7 @@ def generate_random_start(model, graph, seed_length=50,new_words=50,diversity=1,
             actual = generated[:] + seq[end_idx:end_idx + new_words]
 
             # Keep adding new words
-            for i in range(new_words):
-
+            for _ in range(new_words):
                 # Make a prediction from the seed
                 preds = model.predict(np.array(seed).reshape(1, -1))[0].astype(np.float64)
 
@@ -54,26 +53,17 @@ def generate_random_start(model, graph, seed_length=50,new_words=50,diversity=1,
                 seed += [next_idx]
                 generated.append(next_idx)
 
-        # Showing generated and actual abstract
-        n = []
-
-        for i in generated:
-            n.append(idx_word.get(i, '==='))
-
+        n = [idx_word.get(i, '===') for i in generated]
         gen_list.append(n)
 
-    a = []
-
-    for i in actual:
-        a.append(idx_word.get(i, '==='))
-
+    a = [idx_word.get(i, '===') for i in actual]
     a = a[seed_length:]
 
     gen_list = [gen[seed_length:seed_length + len(a)] for gen in gen_list]
 
     if return_output:
         return original_sequence, gen_list, a
-	
+
     # HTML formatting
     seed_html = ''
     seed_html = addContent(seed_html, header(
@@ -87,16 +77,14 @@ def generate_random_start(model, graph, seed_length=50,new_words=50,diversity=1,
     a_html = ''
     a_html = addContent(a_html, header('Actual', color='darkgreen'))
     a_html = addContent(a_html, box(remove_spaces(' '.join(a))))
-
-    st = "<div>" + seed_html + "</div><div>" + gen_html + "</div><div>" + a_html + "</div>" 
-    #return f"<div>{seed_html}</div><div>{gen_html}</div><div>{a_html}</div>"
-    return st
+
+    return f"<div>{seed_html}</div><div>{gen_html}</div><div>{a_html}</div>"
 
 def generate_from_seed(model, graph, seed,new_words=50, diversity=0.75):
     """Generate output from a sequence"""
 
     # Mapping of words to integers
-    word_idx = json.load(open('data/word-index.json')) 
+    word_idx = json.load(open('data/word-index.json'))
     idx_word = {idx: word for word, idx in word_idx.items()}
 
     # Original formated text
@@ -133,33 +121,33 @@ def generate_from_seed(model, graph, seed,new_words=50, diversity=0.75):
     html = addContent(html, header(
         'Input Seed ', color='black', gen_text='Network Output'))
     html = addContent(html, box(start, gen))
-    st = "<div>"+html+"</div>"
-    return st
+    return f"<div>{html}</div>"
 
 
 def header(text, color='black', gen_text=None):
     """Create an HTML header"""
 
-    if gen_text:
-        raw_html = '<h1 style="margin-top:16px;color: {color};font-size:54px"><center>' + str(
-            text) + '<span style="color: red">' + str(gen_text) + '</center></h1>'
-    else:
-        raw_html = '<h1 style="margin-top:12px;color: {color};font-size:54px"><center>' + str(
-            text) + '</center></h1>'
-    return raw_html
+    return (
+        '<h1 style="margin-top:16px;color: {color};font-size:54px"><center>'
+        + str(text)
+        + '<span style="color: red">'
+        + str(gen_text)
+        + '</center></h1>'
+        if gen_text
+        else '<h1 style="margin-top:12px;color: {color};font-size:54px"><center>'
+        + str(text)
+        + '</center></h1>'
+    )
 
 
 def box(text, gen_text=None):
     """Create an HTML box of text"""
 
-    if gen_text:
-        raw_html = '<div style="padding:8px;font-size:28px;margin-top:28px;margin-bottom:14px;">' + str(
-            text) + '<span style="color: red">' + str(gen_text) + '</div>'
-
-    else:
-        raw_html = '<div style="border-bottom:1px inset black;border-top:1px inset black;padding:8px;font-size: 28px;">' + str(
-            text) + '</div>'
-    return raw_html
+    return (
+        f'<div style="padding:8px;font-size:28px;margin-top:28px;margin-bottom:14px;">{str(text)}<span style="color: red">{str(gen_text)}</div>'
+        if gen_text
+        else f'<div style="border-bottom:1px inset black;border-top:1px inset black;padding:8px;font-size: 28px;">{str(text)}</div>'
+    )
 
 
 def addContent(old_html, raw_html):

diff --git a/Memory-profiling/Scalene/linearmodel.py b/Memory-profiling/Scalene/linearmodel.py
@@ -11,7 +11,11 @@
 def make_data():
     X,y = make_regression(n_samples=NUM_SAMPLES,n_features=NUM_FEATURES,
                       n_informative=NUM_FEATURES,noise=0.5)
-    data = pd.DataFrame(X,columns=['X'+str(i) for i in range(1,NUM_FEATURES+1)],dtype=np.float16)
+    data = pd.DataFrame(
+        X,
+        columns=[f'X{str(i)}' for i in range(1, NUM_FEATURES + 1)],
+        dtype=np.float16,
+    )
     data['y']=np.array(y,dtype=np.float16)
     return data
 

diff --git a/Memory-profiling/Scalene/mlp.py b/Memory-profiling/Scalene/mlp.py
@@ -11,7 +11,11 @@
 def make_data():
     X,y = make_regression(n_samples=NUM_SAMPLES,n_features=NUM_FEATURES,
                       n_informative=NUM_FEATURES,noise=0.5)
-    data = pd.DataFrame(X,columns=['X'+str(i) for i in range(1,NUM_FEATURES+1)],dtype=np.float16)
+    data = pd.DataFrame(
+        X,
+        columns=[f'X{str(i)}' for i in range(1, NUM_FEATURES + 1)],
+        dtype=np.float16,
+    )
     data['y']=np.array(y,dtype=np.float16)
     return data
 

diff --git a/OOP_in_ML/Class_MyLinearRegression.py b/OOP_in_ML/Class_MyLinearRegression.py
@@ -101,7 +101,6 @@ def summary_metrics(self):
         if not self.is_fitted:
             print("Model not fitted yet!")
             return None
-        metrics = {}
         items = (
             ("sse", self.sse()),
             ("sst", self.sst()),
@@ -111,9 +110,7 @@ def summary_metrics(self):
             ("AIC:", self.aic()),
             ("BIC:", self.bic()),
         )
-        for item in items:
-            metrics[item[0]] = item[1]
-        return metrics
+        return {item[0]: item[1] for item in items}
 
 
 class Inference:
@@ -208,10 +205,7 @@ def fitted_vs_features(self):
             print("Model not fitted yet!")
             return None
         num_plots = self.features_.shape[1]
-        if num_plots % 3 == 0:
-            nrows = int(num_plots / 3)
-        else:
-            nrows = int(num_plots / 3) + 1
+        nrows = int(num_plots / 3) if num_plots % 3 == 0 else int(num_plots / 3) + 1
         ncols = 3
         fig, ax = plt.subplots(nrows, ncols, figsize=(15, nrows * 3.5))
         axes = ax.ravel()
@@ -226,7 +220,7 @@ def fitted_vs_features(self):
                 alpha=0.8,
             )
             axes[i].grid(True)
-            axes[i].set_xlabel("Feature X[{}]".format(i))
+            axes[i].set_xlabel(f"Feature X[{i}]")
             axes[i].set_ylabel("Residuals")
             axes[i].hlines(
                 y=0,
@@ -412,7 +406,7 @@ def vif(self):
         lm = sm.OLS(self.target_, sm.add_constant(self.features_)).fit()
         for i in range(self.features_.shape[1]):
             v = vif(np.matrix(self.features_), i)
-            print("Variance inflation factor for feature {}: {}".format(i, round(v, 2)))
+            print(f"Variance inflation factor for feature {i}: {round(v, 2)}")
 
 
 class MyLinearRegression(

diff --git a/Pytest/linear_model.py b/Pytest/linear_model.py
@@ -31,14 +31,14 @@ def train_linear_model(X,y,
         # Fit
         model.fit(X_train, y_train)
         # Save
-        fname = filename+'.sav'
+        fname = f'{filename}.sav'
         dump(model, fname)
         # Compute scores
         r2_train = model.score(X_train,y_train)
         r2_test = model.score(X_test,y_test)
         # Return scores in a dictionary
         return {'Train-score':r2_train, 'Test-score': r2_test}
-    
+
     except AssertionError as msg: 
         print(msg)
         return msg