shreenath-ml-scripts 0.1.0__py3-none-any.whl

ml_prac_scripts/eda.py

@@ -0,0 +1,65 @@
+# -*- coding: utf-8 -*-
+"""eda.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1Fm6OC_xJb4m29eC8pGFUqGFzpMxKvUiA
+"""
+
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+df = sns.load_dataset("titanic")
+
+df.head()
+
+df.info()
+
+df.describe()
+
+df.isnull().sum()
+
+df["age"] = df["age"].fillna(df["age"].median())
+
+df['embarked'] = df['embarked'].fillna(df['embarked'].mode()[0])
+
+df.drop('deck', axis=1, inplace=True)
+
+df.dropna(inplace=True)
+
+df.info()
+
+sns.boxplot(x=df['fare'])
+plt.title('Fare Boxplot (Before Handling Outliers)')
+plt.show()
+
+Q1 = df['fare'].quantile(0.25)
+Q3 = df['fare'].quantile(0.75)
+IQR = Q3 - Q1
+
+lower_bound = Q1 - 1.5 * IQR
+upper_bound = Q3 + 1.5 * IQR
+
+df['fare'] = np.where(df['fare'] > upper_bound, upper_bound, np.where(df['fare'] < lower_bound, lower_bound, df['fare']))
+
+print(f"Outliers capped at: {upper_bound}")
+
+df['log_fare'] = np.log1p(df['fare'])
+
+plt.figure(figsize=(10,4))
+plt.subplot(1, 2, 1)
+sns.histplot(df['fare'], kde=True).set_title('Original Fare')
+plt.subplot(1, 2, 2)
+sns.histplot(df['log_fare'], kde=True).set_title('Log Transformed Fare')
+plt.show()
+
+df['sex'] = df['sex'].map({'male': 0, 'female': 1})
+
+df = pd.get_dummies(df, columns=['embarked'], drop_first=True)
+
+print("\nFinal Dataframe Head:")
+print(df[['survived', 'pclass', 'sex', 'age', 'log_fare', 'embarked_Q', 'embarked_S']].head())
+

ml_prac_scripts/kmeansclustering.py

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+"""KMeansClustering.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1Yt6p5RJKdDBlYIy11bsGPmTO5cJ6kdnA
+"""
+
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.cluster import KMeans
+from sklearn.preprocessing import LabelEncoder
+from sklearn.preprocessing import StandardScaler
+import warnings
+import seaborn as sns
+warnings.filterwarnings("ignore")
+
+df = pd.read_csv("sales.csv", encoding='latin-1')
+df.head()
+
+scaler = StandardScaler()
+
+df_numeric = df.select_dtypes(include=np.number)
+X_scaled = scaler.fit_transform(df_numeric)
+
+inertia = []
+for k in range(1, 11):
+  k_means = KMeans(n_clusters=k, random_state=42, n_init=10)
+  k_means.fit(X_scaled)
+  inertia.append(k_means.inertia_)
+
+plt.figure(figsize=(8, 5))
+sns.lineplot(x=range(1, 11), y=inertia, marker='o', linestyle='-')
+plt.title('Elbow Method for Optimal k')
+plt.xlabel('Number of Clusters (k)')
+plt.ylabel('Inertia')
+
+optimal_k = 3
+kmeans = KMeans(n_clusters=optimal_k, random_state=42, n_init=10)
+kmeans.fit(X_scaled)
+labels = kmeans.labels_
+
+plt.figure(figsize=(10, 6))
+sns.scatterplot(x=X_scaled[:, 0], y=X_scaled[:, 1], hue=labels)
+

ml_prac_scripts/knn.py

@@ -0,0 +1,36 @@
+# -*- coding: utf-8 -*-
+"""knn.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1u49MdRl6i0Jlmx9I1gm1iYjiHEXGI97C
+"""
+
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.metrics import accuracy_score, confusion_matrix, recall_score, f1_score, precision_score
+
+url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"
+column_names = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species']
+df = pd.read_csv(url, names=column_names)
+
+label_enoder = LabelEncoder()
+df['species'] = label_enoder.fit_transform(df['species'])
+
+X = df.drop('species', axis=1)
+y = df['species']
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+
+knn = KNeighborsClassifier(n_neighbors=3)
+knn.fit(X_train, y_train)
+
+y_pred = knn.predict(X_test)
+
+print("Accuracy:", accuracy_score(y_test, y_pred))
+print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))
+

ml_prac_scripts/linear_regression.py

@@ -0,0 +1,58 @@
+# -*- coding: utf-8 -*-
+"""linear_regression.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1AqzDrmjgKq5uD5lNbJdJJFdzGUUCW3hs
+"""
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error, r2_score
+from sklearn.preprocessing import StandardScaler
+
+df = pd.read_csv("HousingData.csv")
+df.head()
+
+df["CRIM"] = df["CRIM"].fillna(df["CRIM"].mean())
+df["ZN"] = df["ZN"].fillna(df["ZN"].mean())
+df["INDUS"] = df["INDUS"].fillna(df["INDUS"].mean())
+df["CHAS"] = df["CHAS"].fillna(df["CHAS"].mean())
+df["AGE"] = df["AGE"].fillna(df["AGE"].mean())
+df["LSTAT"] = df["LSTAT"].fillna(df["LSTAT"].mean())
+
+df.info()
+
+X = df.drop('MEDV', axis=1)
+y = df['MEDV']
+X_scaled = StandardScaler().fit_transform(X)
+X_scaled
+
+X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
+
+model = LinearRegression()
+model.fit(X_train, y_train)
+y_pred = model.predict(X_test)
+y_pred
+
+mse = mean_squared_error(y_test, y_pred)
+r2 = r2_score(y_test, y_pred)
+print("Mean Squared Error:", mse)
+print("R-squared:", r2)
+
+plt.figure(figsize=(10, 6))
+plt.scatter(y_test, y_pred)
+plt.xlabel("Actual Values")
+plt.ylabel("Predicted Values")
+plt.title("Actual vs. Predicted Values")
+
+# Add the line of best fit (y=x)
+plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], '-', lw=1)
+plt.plot([y_pred.min(), y_pred.max()], [y_pred.min(), y_pred.max()], '-', lw=1)
+
+plt.show()
+

ml_prac_scripts/logistic_regression.py

@@ -0,0 +1,58 @@
+# -*- coding: utf-8 -*-
+"""logistic_regression.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1_9gGFH3ONYSD_saWKC9Vf2wJ-YU3if1G
+"""
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.preprocessing import MinMaxScaler, LabelEncoder
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+import seaborn as sns
+
+df = pd.read_csv("Social_Network_Ads.csv")
+numeric_columns = ['Age', 'EstimatedSalary']
+df.head()
+
+scaler = MinMaxScaler()
+scaled = scaler.fit_transform(df[numeric_columns])
+scaled = pd.DataFrame(scaled, columns=numeric_columns)
+scaled
+
+label_encoder = LabelEncoder()
+encoded = df.copy()
+encoded['Gender'] = label_encoder.fit_transform(df['Gender'])
+encoded
+
+X = scaled
+X['Gender'] = encoded['Gender']
+y = df['Purchased']
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+model = LogisticRegression()
+
+model.fit(X_train, y_train)
+
+y_pred = model.predict(X_test)
+
+accuracy = accuracy_score(y_test, y_pred)
+print(f"Accuracy: {accuracy:.4f}\n")
+
+print("Classification Report:")
+
+print(classification_report(y_test, y_pred, target_names=['Not Purchased (0)', 'Purchased (1)']))
+
+print("Confusion Matrix:")
+
+print(confusion_matrix(y_test, y_pred))
+cm = confusion_matrix(y_test, y_pred)
+sns.heatmap(cm, annot=True, fmt='d', cmap="Blues")
+

ml_prac_scripts/pca.py

@@ -0,0 +1,86 @@
+# -*- coding: utf-8 -*-
+"""pca.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1vS6JOW2HWZiPOYrryS6XDOjq0G3Ja_9y
+"""
+
+import pandas as pd
+import numpy as np
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+import matplotlib.pyplot as plt
+
+df = pd.read_csv("Iris.csv")
+df.columns = ["id", "sepal_length", "sepal_width", "petal_length", "petal_width", "species"]
+df.head()
+
+features = ["sepal_length", "sepal_width", "petal_length", "petal_width"]
+x = df.loc[:, features].values
+y = df.loc[:, ["species"]].values
+
+x = StandardScaler().fit_transform(x)
+
+pca = PCA(n_components=2)
+principal_components = pca.fit_transform(x)
+principal_components
+
+principalDF = pd.DataFrame(data = principal_components, columns=["pc1", "pc2"])
+final = pd.concat([principalDF, df[["species"]]], axis=1)
+final.head()
+
+plt.figure()
+plt.xlabel("pc1")
+plt.ylabel("pc2")
+plt.title("2 component PCA")
+targets = ["Iris-setosa", "Iris-versicolor", "Iris-virginica"]
+colors = ["r", "g", "b"]
+for target, color in zip(targets, colors):
+    indicesToKeep = final["species"] == target
+    plt.scatter(final.loc[indicesToKeep, "pc1"], final.loc[indicesToKeep, "pc2"], c=color, s=50)
+plt.legend(targets)
+plt.grid()
+plt.show()
+
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+
+df = pd.read_csv("Iris.csv")
+df.info()
+
+df.columns = ["id", "speal_len", "sepal_width", "petal_len", "petal_width", "species"]
+features = ["speal_len", "sepal_width", "petal_len", "petal_width"]
+
+X = df.loc[:, features].values
+y = df.loc[:, ["species"]].values
+
+# X = StandardScaler().fit_transform(X)
+
+pca = PCA(n_components=2)
+p_com = pca.fit_transform(X)
+
+p_df = pd.DataFrame(data=p_com, columns=["pca1", "pc2"])
+final = pd.concat([p_df, df[["species"]]], axis=1)
+
+plt.figure()
+plt.xlabel("pc1")
+plt.ylabel("pc2")
+plt.title("2 components PCA")
+targets = ["Iris-setosa", "Iris-versicolor", "Iris-virginica"]
+colors = ["r", "g", "b"]
+
+for t, c in zip(targets, colors):
+  indices = final["species"] == t
+  plt.scatter(
+      final.loc[indices, "pca1"],
+      final.loc[indices, "pc2"],
+      c=c,
+      s=50
+  )
+plt.legend(targets)
+

ml_prac_scripts/svm.py

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+"""svm.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1gtCM25ZOphz_jwcev_e6g8YH-yMt5RDP
+"""
+
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.svm import SVC
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+from sklearn.preprocessing import StandardScaler
+from sklearn.feature_extraction.text import TfidfVectorizer
+import seaborn as sns
+
+df = pd.read_csv("emails.csv")
+df.dropna()
+df = df.drop(columns=["Email No."])
+df.isna().sum()
+
+vectorizer = TfidfVectorizer(stop_words='english')
+
+X = vectorizer.fit_transform(df)
+
+X = df.drop(columns=['Prediction'])
+y = df['Prediction']
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+
+model = SVC(kernel='linear', C=1.0, random_state=42)
+model.fit(X_train, y_train)
+
+y_pred = model.predict(X_test)
+
+print("Accuracy:", accuracy_score(y_test, y_pred))
+print("\nClassification Report:\n")
+print(classification_report(y_test, y_pred))
+print("\nConfusion Matrix:\n")
+print(confusion_matrix(y_test, y_pred))
+cm = confusion_matrix(y_test, y_pred)
+
+sns.heatmap(
+    cm,
+    annot=True,
+    fmt='d',
+    cmap='Blues',
+    xticklabels=['Not Spam', 'Spam'],
+    yticklabels=['Not Spam', 'Spam']
+)
+

shreenath_ml_scripts-0.1.0.dist-info/METADATA

@@ -0,0 +1,16 @@
+Metadata-Version: 2.4
+Name: shreenath-ml-scripts
+Version: 0.1.0
+Summary: A collection of machine learning scripts
+Author: Shreenath
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: matplotlib
+Requires-Dist: scikit-learn
+Requires-Dist: seaborn
+Dynamic: author
+Dynamic: classifier
+Dynamic: requires-dist
+Dynamic: summary

shreenath_ml_scripts-0.1.0.dist-info/RECORD

@@ -0,0 +1,12 @@
+ml_prac_scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ml_prac_scripts/eda.py,sha256=p-F5SkONgMznpSjgP4JCPcm5NToN8-nLAlYtp2wBc-s,1455
+ml_prac_scripts/kmeansclustering.py,sha256=QwJngX7XTOzVDye3SokpQWJyv1-urZTzIKHWqZjYnvw,1224
+ml_prac_scripts/knn.py,sha256=srSgSePCgpfSu4FmVIRlDuT4SSQQgPqd1n-T0VU-dxM,1134
+ml_prac_scripts/linear_regression.py,sha256=3X7nYTzHlaWM3kt45_67xYyOO5nJXBcsoubT2lc6mRs,1618
+ml_prac_scripts/logistic_regression.py,sha256=Hc7BfXujLDDnYX1r0ahdljyyjcEx_QMQI-BvHLGICHI,1541
+ml_prac_scripts/pca.py,sha256=Tc5p8fWmS_XdJTqePDrb1muqlPnGaxTGSLeotoglP48,2287
+ml_prac_scripts/svm.py,sha256=JIAO-J2MmxyRt9OJPcdVobEUQRX79a-w7Uxk7jfxnhw,1334
+shreenath_ml_scripts-0.1.0.dist-info/METADATA,sha256=lemZTBdSNZXVP_z4G90iX74oa6kXpOeJm7anC2S-0VY,427
+shreenath_ml_scripts-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+shreenath_ml_scripts-0.1.0.dist-info/top_level.txt,sha256=QxnhFgPBYlkHDXciaFOgFraw4_XX7-if-yAL_maKmEY,16
+shreenath_ml_scripts-0.1.0.dist-info/RECORD,,

shreenath_ml_scripts-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

shreenath_ml_scripts-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+ml_prac_scripts