Elvarix 1.0.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,5 @@
1
+ Metadata-Version: 2.4
2
+ Name: Elvarix
3
+ Version: 1.0.0
4
+ Summary: ML Lab practicals 1-8: show(n) prints the code
5
+ Requires-Python: >=3.7
@@ -0,0 +1,6 @@
1
+ pyproject.toml
2
+ Elvarix.egg-info/PKG-INFO
3
+ Elvarix.egg-info/SOURCES.txt
4
+ Elvarix.egg-info/dependency_links.txt
5
+ Elvarix.egg-info/top_level.txt
6
+ elvarix/__init__.py
@@ -0,0 +1 @@
1
+ elvarix
elvarix-1.0.0/PKG-INFO ADDED
@@ -0,0 +1,5 @@
1
+ Metadata-Version: 2.4
2
+ Name: Elvarix
3
+ Version: 1.0.0
4
+ Summary: ML Lab practicals 1-8: show(n) prints the code
5
+ Requires-Python: >=3.7
@@ -0,0 +1,211 @@
1
+ """Elvarix: ML Lab practicals. Usage: from elvarix import show; show(1)"""
2
+
3
+ __all__ = ["show", "PRACTICALS"]
4
+
5
+ PRACTICALS = {
6
+ 1: ("Data preprocessing (heart dataset)", r'''import pandas as pd
7
+ from sklearn.preprocessing import LabelEncoder
8
+ from sklearn.model_selection import train_test_split
9
+
10
+ df = pd.read_csv("Heart.csv")
11
+
12
+ # a. Data cleaning
13
+ df = df.drop(columns=["Unnamed: 0"]).drop_duplicates()
14
+
15
+ # b. Handling missing data
16
+ print(df.isnull().sum())
17
+ df = df.fillna(df.mode().iloc[0])
18
+
19
+ # c. Data transformation
20
+ for c in ["ChestPain", "Thal", "AHD"]:
21
+ df[c] = LabelEncoder().fit_transform(df[c])
22
+
23
+ # d. Train 75% / test 25%
24
+ x = df.drop(columns="AHD")
25
+ y = df["AHD"]
26
+ x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
27
+ print(x_train.shape, x_test.shape)
28
+ '''),
29
+ 2: ("Confusion matrix (COVID)", r'''tp, fp, fn = 45, 55, 5
30
+ tn = 500 - tp - fp - fn
31
+ print("Confusion matrix [[TP, FN], [FP, TN]]:", [[tp, fn], [fp, tn]])
32
+
33
+ p = tp / (tp + fp)
34
+ r = tp / (tp + fn)
35
+ print("Accuracy:", (tp + tn) / 500)
36
+ print("Precision:", p)
37
+ print("Recall:", r)
38
+ print("F1 score:", 2 * p * r / (p + r))
39
+ '''),
40
+ 3: ("Decision tree (GRE admission)", r'''import pandas as pd
41
+ import matplotlib.pyplot as plt
42
+ from sklearn.model_selection import train_test_split
43
+ from sklearn.tree import DecisionTreeClassifier, plot_tree
44
+ from sklearn.metrics import accuracy_score, confusion_matrix, ConfusionMatrixDisplay
45
+
46
+ df = pd.read_csv("Admission_Predict.csv")
47
+
48
+ # a. Pre-processing: chance (0 to 1) -> admitted 0/1
49
+ df["Chance of Admit "] = (df["Chance of Admit "] >= 0.5).astype(int)
50
+
51
+ # b. Train-test split
52
+ x = df.drop(columns=["Serial No.", "Chance of Admit "])
53
+ y = df["Chance of Admit "]
54
+ x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
55
+
56
+ # c. Decision tree + evaluate
57
+ model = DecisionTreeClassifier().fit(x_train, y_train)
58
+ y_pred = model.predict(x_test)
59
+ print("Accuracy:", accuracy_score(y_test, y_pred))
60
+ print(confusion_matrix(y_test, y_pred))
61
+
62
+ # Graphs: confusion matrix + tree (top 2 levels)
63
+ ConfusionMatrixDisplay.from_predictions(y_test, y_pred)
64
+ plt.show()
65
+ plt.figure(figsize=(14, 7))
66
+ plot_tree(model, max_depth=2, feature_names=list(x.columns), filled=True)
67
+ plt.show()
68
+ '''),
69
+ 4: ("Logistic regression (personal loan)", r'''import pandas as pd
70
+ import matplotlib.pyplot as plt
71
+ from sklearn.model_selection import train_test_split
72
+ from sklearn.linear_model import LogisticRegression
73
+ from sklearn.metrics import accuracy_score, confusion_matrix, ConfusionMatrixDisplay
74
+
75
+ df = pd.read_csv("Bank_Personal_Loan_Modelling.csv")
76
+ df = df.replace("/", ".", regex=True).astype(float)
77
+
78
+ x = df.drop(columns=["ID", "ZIP Code", "Personal Loan"])
79
+ y = df["Personal Loan"]
80
+ x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
81
+
82
+ model = LogisticRegression(max_iter=5000).fit(x_train, y_train)
83
+ y_pred = model.predict(x_test)
84
+ print("Accuracy:", accuracy_score(y_test, y_pred))
85
+ print(confusion_matrix(y_test, y_pred))
86
+
87
+ # Graph: confusion matrix
88
+ ConfusionMatrixDisplay.from_predictions(y_test, y_pred)
89
+ plt.show()
90
+ '''),
91
+ 5: ("Linear regression (India temperatures)", r'''import pandas as pd
92
+ import matplotlib.pyplot as plt
93
+ from sklearn.linear_model import LinearRegression
94
+ from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
95
+
96
+ df = pd.read_csv("temperatures.csv")
97
+ x = df[["YEAR"]]
98
+
99
+ # a + b. Predict each month, print MSE, MAE, R2
100
+ for m in df.columns[1:13]:
101
+ y = df[m]
102
+ y_pred = LinearRegression().fit(x, y).predict(x)
103
+ print(m, mean_squared_error(y, y_pred), mean_absolute_error(y, y_pred),
104
+ r2_score(y, y_pred))
105
+
106
+ # c. Visualize (last month in loop = DEC)
107
+ plt.scatter(x, y)
108
+ plt.plot(x, y_pred, color="red")
109
+ plt.xlabel("Year"); plt.ylabel("Temperature (°C)")
110
+ plt.show()
111
+ '''),
112
+ 6: ("SMS spam filter (Naive Bayes)", r'''import pandas as pd
113
+ from sklearn.preprocessing import LabelEncoder
114
+ from sklearn.feature_extraction.text import CountVectorizer
115
+ from sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV
116
+ from sklearn.naive_bayes import MultinomialNB
117
+ from sklearn.linear_model import LogisticRegression
118
+ from sklearn.metrics import accuracy_score
119
+
120
+ df = pd.read_csv("SMSSpamCollection", sep="\t", names=["label", "msg"], quoting=3)
121
+
122
+ # a. Pre-processing: ham/spam -> 0/1, text -> word counts
123
+ y = LabelEncoder().fit_transform(df["label"])
124
+ x = CountVectorizer().fit_transform(df["msg"])
125
+
126
+ # b. Train-test split
127
+ x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
128
+
129
+ # c + d. Two models: accuracy and cross-validation
130
+ models = {"NB": MultinomialNB(), "LR": LogisticRegression(max_iter=1000)}
131
+ for name, model in models.items():
132
+ model.fit(x_train, y_train)
133
+ print(name, "Accuracy:", accuracy_score(y_test, model.predict(x_test)))
134
+ print(name, "CV:", cross_val_score(model, x, y, cv=5).mean())
135
+
136
+ # e. Hyperparameter tuning
137
+ params = {"NB": {"alpha": [0.1, 0.5, 1]}, "LR": {"C": [0.1, 1, 10]}}
138
+ for name, model in models.items():
139
+ g = GridSearchCV(model, params[name], cv=5).fit(x_train, y_train)
140
+ print(name, "Best:", g.best_params_)
141
+ print(name, "Tuned:", accuracy_score(y_test, g.predict(x_test)))
142
+ '''),
143
+ 7: ("Clustering (mall customers)", r'''import pandas as pd
144
+ import matplotlib.pyplot as plt
145
+ from sklearn.preprocessing import LabelEncoder
146
+ from sklearn.model_selection import train_test_split
147
+ from sklearn.cluster import KMeans, AgglomerativeClustering
148
+
149
+ df = pd.read_csv("Mall_Customers.csv")
150
+
151
+ # a. Pre-processing
152
+ df["Genre"] = LabelEncoder().fit_transform(df["Genre"])
153
+
154
+ # b. Train-test split
155
+ x = df[["Annual Income (k$)", "Spending Score (1-100)"]]
156
+ x_train, x_test = train_test_split(x, test_size=0.25)
157
+
158
+ # Algorithm 1: K-Means
159
+ km = KMeans(n_clusters=5, n_init=10).fit(x_train)
160
+ print(x_train.groupby(km.labels_).mean())
161
+ print("Test clusters:", km.predict(x_test))
162
+ plt.scatter(x_train.iloc[:, 0], x_train.iloc[:, 1], c=km.labels_)
163
+ plt.xlabel("Annual Income"); plt.ylabel("Spending Score"); plt.title("K-Means")
164
+ plt.show()
165
+
166
+ # Algorithm 2: Agglomerative
167
+ ag = AgglomerativeClustering(n_clusters=5).fit(x_train)
168
+ print(x_train.groupby(ag.labels_).mean())
169
+ plt.scatter(x_train.iloc[:, 0], x_train.iloc[:, 1], c=ag.labels_)
170
+ plt.xlabel("Annual Income"); plt.ylabel("Spending Score"); plt.title("Agglomerative")
171
+ plt.show()
172
+ '''),
173
+ 8: ("Association rules (Apriori)", r'''# Run once first: !pip install apyori
174
+ import pandas as pd
175
+ from apyori import apriori
176
+
177
+ # a. Data preprocessing
178
+ df = pd.read_csv("Market_Basket_Optimisation.csv", header=None)
179
+
180
+ # b. List of transactions (skip empty cells)
181
+ transactions = [[str(i) for i in row if str(i) != "nan"] for row in df.values]
182
+
183
+ # c. Train Apriori
184
+ rules = list(apriori(transactions, min_support=0.003,
185
+ min_confidence=0.2, min_lift=3))
186
+
187
+ # d. Visualize rules
188
+ for r in rules:
189
+ s = r.ordered_statistics[0]
190
+ print(list(s.items_base), "->", list(s.items_add))
191
+ print(" confidence:", round(s.confidence, 2), "lift:", round(s.lift, 2))
192
+
193
+ # e. Rules change with hyperparameters
194
+ for c in [0.2, 0.3, 0.4]:
195
+ r = list(apriori(transactions, min_support=0.003,
196
+ min_confidence=c, min_lift=3))
197
+ print("min_confidence", c, "-> rules:", len(r))
198
+ '''),
199
+ }
200
+
201
+
202
+ def show(n=None):
203
+ """Print code of practical n (1-8). No argument: list all practicals."""
204
+ if n is None:
205
+ for k, (title, _) in PRACTICALS.items():
206
+ print(f"{k}. {title}")
207
+ return
208
+ if n not in PRACTICALS:
209
+ raise ValueError("Practical number must be 1-8")
210
+ title, code = PRACTICALS[n]
211
+ print(f"# P{n}. {title}\n\n{code}")
@@ -0,0 +1,12 @@
1
+ [build-system]
2
+ requires = ["setuptools>=61"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "Elvarix"
7
+ version = "1.0.0"
8
+ description = "ML Lab practicals 1-8: show(n) prints the code"
9
+ requires-python = ">=3.7"
10
+
11
+ [tool.setuptools]
12
+ packages = ["elvarix"]
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+