nummpyy 1.0.0__py3-none-any.whl

nummpyy/__init__.py

@@ -0,0 +1,35 @@
+import os
+import sys
+
+def show_codes(filename: str = None):
+    """
+    Displays code included in this package.
+    - If filename is given (without .py), shows that file's code.
+    - If no filename is given, shows all .py files.
+    """
+    base_path = os.path.dirname(__file__)
+    files = [f for f in os.listdir(base_path) if f.endswith(".py") and f != "__init__.py"]
+
+    if filename:
+        file_path = os.path.join(base_path, f"{filename}.py")
+        if os.path.exists(file_path):
+            print(f"\n=== Showing {filename}.py ===\n")
+            with open(file_path, "r", encoding="utf-8") as f:
+                print(f.read())
+        else:
+            print(f"\n❌ File '{filename}.py' not found in this package.\n")
+            print("Available files:")
+            for f in files:
+                print("•", f.replace(".py", ""))
+    else:
+        print("\nAll practical codes:\n")
+        for f in files:
+            print(f"\n=== {f} ===\n")
+            with open(os.path.join(base_path, f), "r", encoding="utf-8") as file:
+                print(file.read())
+
+
+def main():
+    """Command-line entry point: nummpyy [filename]"""
+    filename = " ".join(sys.argv[1:]) or None
+    show_codes(filename)

nummpyy/assesssuperstep.py

@@ -0,0 +1,55 @@
+import os
+import numpy as np
+import pandas as pd
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def _fruit_df():
+    return pd.DataFrame(
+        [[10, np.nan, 30, 40],
+         [7, 14, 21, 28],
+         [55, np.nan, 8, 12],
+         [15, 14, np.nan, 8],
+         [7, 1, 1, np.nan],
+         [np.nan, 4, 9, 2]],
+        columns=["Apple", "Orange", "Banana", "Pear"],
+        index=["Basket1", "Basket2", "Basket3", "Basket4", "Basket5", "Basket6"])
+
+
+def p6():
+    print("#################################")
+    print("THE ORIGINAL VALUES")
+    print(_fruit_df())
+
+    df = _fruit_df()
+    print("\nREPLACING THE VALUES WITH MEAN")
+    df.fillna(df.mean(), inplace=True)
+    print(df)
+
+    df = _fruit_df()
+    print("\nREPLACING THE VALUES WITH MEDIAN")
+    df.fillna(df.median(), inplace=True)
+    print(df)
+
+    df = _fruit_df()
+    print("\nREPLACING THE VALUES WITH MODE")
+    for column in df.columns:
+        df[column] = df[column].fillna(df[column].mode()[0])
+    print(df)
+
+    df = _fruit_df()
+    print("\nREPLACING THE VALUES WITH MINIMUM")
+    df.fillna(df.min(), inplace=True)
+    print(df)
+
+
+if __name__ == "__main__":
+    p6()

nummpyy/averagelatitude.py

@@ -0,0 +1,30 @@
+import os
+import pandas as pd
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def load_ip_data():
+    df = pd.read_csv(path("IP_DATA_ALL.csv"), header=0, low_memory=False,
+                     encoding="latin-1",
+                     usecols=["Country", "Place.Name", "Latitude", "Longitude"])
+    df.rename(columns={"Place.Name": "Place_Name"}, inplace=True)
+    return df
+
+
+def p2e():
+    IP_DATA_ALL = load_ip_data()
+    small = IP_DATA_ALL[["Country", "Place_Name", "Latitude"]]
+    AverageLatitude = small.groupby(["Country", "Place_Name"])["Latitude"].mean()
+    print(AverageLatitude)
+
+
+if __name__ == "__main__":
+    p2e()

nummpyy/correlation.py

@@ -0,0 +1,43 @@
+import os
+import pandas as pd
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p14():
+    # If your files are real Excel files, change read_csv to read_excel
+    math = pd.read_csv(path("students_math.csv"))
+    science = pd.read_csv(path("student_science.csv"))
+
+    print("Math Dataset:")
+    print(math)
+    print("\nScience Dataset:")
+    print(science)
+
+    data = pd.merge(math, science, on="Student_ID")
+    print("\nMerged Dataset:")
+    print(data)
+
+    correlation = data["Math"].corr(data["Science"])
+    print("\nCorrelation between Math and Science =", round(correlation, 2))
+
+    print("\nCorrelation Matrix:")
+    print(data[["Math", "Science"]].corr())
+
+    plt.scatter(data["Math"], data["Science"])
+    plt.xlabel("Math Marks")
+    plt.ylabel("Science Marks")
+    plt.title("Correlation between Math and Science Marks")
+    plt.show()
+
+
+if __name__ == "__main__":
+    p14()

nummpyy/datascience.py

@@ -0,0 +1,58 @@
+import os
+import numpy as np
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p4():
+    # Histogram
+    y = [10, 5, 8, 4, 2]
+    plt.hist(y)
+    plt.title("Histogram")
+    plt.show()
+
+    # Pie chart (simple)
+    y = np.array([35, 25, 25, 15])
+    plt.pie(y)
+    plt.title("Pie Chart")
+    plt.show()
+
+    # Pie chart (labels, explode, shadow)
+    labels = ["apple", "banana", "cherry", "durian", "elderberries", "figs", "grapes"]
+    sizes = [32, 20, 15, 10, 10, 8, 5]
+    p = plt.pie(sizes, labels=labels, explode=(0.07, 0, 0, 0, 0, 0, 0),
+                autopct="%1.1f%%", startangle=130, shadow=True)
+    plt.axis("equal")
+    for text in p[1]:
+        text.set_fontsize(12)
+    plt.show()
+
+    # Line chart with grid
+    x = np.array([80, 85, 90, 95, 100, 105, 110, 115, 120, 125])
+    y = np.array([240, 250, 260, 270, 280, 290, 300, 310, 320, 330])
+    plt.title("Sports Watch Data")
+    plt.xlabel("Average Pulse")
+    plt.ylabel("Calorie Burnage")
+    plt.plot(x, y)
+    plt.grid()
+    plt.show()
+
+    # Stairs
+    y = [4.8, 5.5, 3.5, 4.6, 6.5, 6.6, 2.6, 3.0]
+    fig, ax = plt.subplots()
+    ax.stairs(y, linewidth=2.5)
+    ax.set(xlim=(0, 8), xticks=np.arange(1, 8),
+           ylim=(0, 8), yticks=np.arange(1, 8))
+    plt.show()
+
+
+if __name__ == "__main__":
+    p4()

nummpyy/edges.py

@@ -0,0 +1,36 @@
+import os
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p10(image_name="1.png"):
+    from PIL import Image
+
+    imageIn = Image.open(path(image_name))
+    fig1 = plt.figure(figsize=(8, 8))
+    fig1.suptitle("Audi R8", fontsize=20)
+    plt.imshow(imageIn)
+    plt.show()
+
+    mask = imageIn.convert("L")
+    th = 49
+    imageOut = mask.point(lambda i: i < th and 255)
+    imageOut.save(path("audi.png"))
+
+    imageTest = Image.open(path("audi.png"))
+    fig2 = plt.figure(figsize=(8, 8))
+    fig2.suptitle("Audi R8 Edge", fontsize=20)
+    plt.imshow(imageTest, cmap="gray")
+    plt.show()
+
+
+if __name__ == "__main__":
+    p10()

nummpyy/extraspaces.py

@@ -0,0 +1,21 @@
+import os
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p2a():
+    baddata = "      Data Science with too many spaces        is great.    "
+    print(">", baddata, "<")
+    cleandata = " ".join(baddata.split())
+    print(">", cleandata, "<")
+
+
+if __name__ == "__main__":
+    p2a()

nummpyy/fixedlatitude.py

@@ -0,0 +1,39 @@
+import os
+import pandas as pd
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def load_ip_data():
+    df = pd.read_csv(path("IP_DATA_ALL.csv"), header=0, low_memory=False,
+                     encoding="latin-1",
+                     usecols=["Country", "Place.Name", "Latitude", "Longitude"])
+    df.rename(columns={"Place.Name": "Place_Name"}, inplace=True)
+    return df
+
+
+def p2d():
+    IP_DATA_ALL = load_ip_data()
+    LondonData = IP_DATA_ALL.loc[IP_DATA_ALL["Place_Name"] == "London"]
+
+    LondonFree = LondonData[["Country", "Place_Name", "Latitude"]].copy()
+    print("Outliers (latitude outside 51.0 to 52.0)")
+    LondonOutliers = LondonFree[(LondonFree["Latitude"] < 51.0) |
+                                (LondonFree["Latitude"] > 52.0)]
+    print(LondonOutliers)
+    print("Total outliers :", len(LondonOutliers))
+
+    print("\nNon-outliers (latitude inside 51.0 to 52.0)")
+    print(LondonFree[(LondonFree["Latitude"] >= 51.0) &
+                     (LondonFree["Latitude"] <= 52.0)])
+
+
+if __name__ == "__main__":
+    p2d()

nummpyy/histogram.py

@@ -0,0 +1,47 @@
+import os
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def load_ip_data():
+    df = pd.read_csv(path("IP_DATA_ALL.csv"), header=0, low_memory=False,
+                     encoding="latin-1",
+                     usecols=["Country", "Place.Name", "Latitude", "Longitude"])
+    df.rename(columns={"Place.Name": "Place_Name"}, inplace=True)
+    return df
+
+
+def p2f():
+    IP_DATA_ALL = load_ip_data()
+    x = IP_DATA_ALL["Latitude"].dropna()
+
+    mu, sigma = x.mean(), x.std()
+    print("Mean:", mu, " Std:", sigma)
+
+    num_bins = 25
+    fig, ax = plt.subplots(figsize=(10, 6))
+    n, bins, patches = ax.hist(x, num_bins, density=True, alpha=0.6)
+
+    # Normal distribution curve (computed with numpy)
+    y = (1 / (sigma * np.sqrt(2 * np.pi))) * np.exp(-0.5 * ((bins - mu) / sigma) ** 2)
+    ax.plot(bins, y, "--", color="red")
+
+    ax.set_xlabel("Latitude")
+    ax.set_ylabel("Probability density")
+    ax.set_title("Histogram of Latitude: mu=%.2f, sigma=%.2f" % (mu, sigma))
+    fig.tight_layout()
+    plt.show()
+
+
+if __name__ == "__main__":
+    p2f()

nummpyy/horus.py

@@ -0,0 +1,36 @@
+import os
+import pandas as pd
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p1b():
+    InputData = pd.read_csv(path("Country.csv"), encoding="latin-1")
+    print("Input Data Values")
+    print(InputData)
+    print("=" * 60)
+
+    ProcessData = InputData.copy()
+    ProcessData.drop(columns=["ISO-2-CODE", "ISO-3-Code"], inplace=True)
+    ProcessData.rename(columns={"Country": "CountryName",
+                                "ISO-M49": "CountryNumber"}, inplace=True)
+    ProcessData.set_index("CountryNumber", inplace=True)
+    ProcessData.sort_values(by="CountryName", ascending=True, inplace=True)
+
+    print("Processed Data")
+    print(ProcessData)
+    print("=" * 60)
+
+    ProcessData.to_csv(path("HORUS-CSV-Country.csv"))
+    print("CSV to HORUS - Done Successfully")
+
+
+if __name__ == "__main__":
+    p1b()

nummpyy/hough.py

@@ -0,0 +1,50 @@
+import os
+import numpy as np
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p7(image_name="hough.jpg"):
+    import cv2
+
+    img = cv2.imread(path(image_name))
+    if img is None:
+        print("Could not read", image_name, "- put it in the same folder.")
+        return
+
+    plt.figure(figsize=(8, 6))
+    plt.title("Original Image")
+    plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
+    plt.axis("off")
+    plt.show()
+
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    edges = cv2.Canny(gray, 50, 200)
+
+    lines = cv2.HoughLinesP(edges, 1, np.pi / 180, 68,
+                            minLineLength=15, maxLineGap=250)
+
+    if lines is not None:
+        for line in lines:
+            x1, y1, x2, y2 = line.flatten()
+            cv2.line(img, (x1, y1), (x2, y2), (255, 0, 0), 3)
+    else:
+        print("No lines detected.")
+
+    plt.figure(figsize=(8, 6))
+    plt.title("Line Detection using Hough Transform")
+    plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
+    plt.axis("off")
+    plt.show()
+
+
+if __name__ == "__main__":
+    p7()

nummpyy/multichannel.py

@@ -0,0 +1,36 @@
+import os
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p9(image_name="1.png"):
+    import matplotlib.image as mpimg
+
+    img = mpimg.imread(path(image_name))
+    print("Size:", img.shape)
+
+    t = 1
+    plt.figure(figsize=(8, 8))
+    plt.title("(" + str(t) + ") Original")
+    plt.imshow(img)
+    plt.show()
+
+    if img.ndim == 3:
+        for c in range(img.shape[2]):
+            t += 1
+            plt.figure(figsize=(8, 8))
+            plt.title("(" + str(t) + ") Channel: " + str(c))
+            plt.imshow(img[:, :, c])
+            plt.show()
+
+
+if __name__ == "__main__":
+    p9()

nummpyy/nlp.py

@@ -0,0 +1,49 @@
+import os
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p8():
+    import nltk
+    nltk.download("punkt")
+    nltk.download("punkt_tab")
+    nltk.download("stopwords")
+
+    from nltk.tokenize import sent_tokenize, word_tokenize
+    from nltk.corpus import stopwords
+    from nltk.probability import FreqDist
+
+    text = """
+    Natural Language Processing (NLP) is a field of Artificial Intelligence.
+    It focuses on the interaction between computers and human language.
+    NLP helps machines understand, interpret, and generate human language.
+    """
+
+    print("Sentence Tokenization:")
+    print(sent_tokenize(text), "\n")
+
+    print("Word Tokenization:")
+    words = word_tokenize(text)
+    print(words, "\n")
+
+    print("Removing Stopwords:")
+    stop_words = set(stopwords.words("english"))
+    filtered_words = [w for w in words
+                      if w.lower() not in stop_words and w.isalnum()]
+    print(filtered_words, "\n")
+
+    print("Frequency Distribution:")
+    fdist = FreqDist(filtered_words)
+    for word, freq in fdist.most_common():
+        print(f"{word}: {freq}")
+
+
+if __name__ == "__main__":
+    p8()

nummpyy/reformatting.py

@@ -0,0 +1,25 @@
+import os
+import datetime
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p2c():
+    baddate = datetime.date(2019, 10, 31)
+    baddata = format(baddate, "%Y-%m-%d")
+    gooddate = datetime.datetime.strptime(baddata, "%Y-%m-%d")
+    gooddata = format(gooddate, "%d %B %Y")
+
+    print("Bad Date  :", baddata)
+    print("Good Date :", gooddata)
+
+
+if __name__ == "__main__":
+    p2c()

nummpyy/removing.py

@@ -0,0 +1,22 @@
+import os
+import string
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p2b():
+    baddata = "Data\x00Science with\x02 funny characters is\x10 great"
+    print("Bad data  :", repr(baddata))
+    cleandata = "".join(filter(lambda x: x in string.printable, baddata))
+    print("Clean data:", repr(cleandata))
+
+
+if __name__ == "__main__":
+    p2b()

nummpyy/retrievesuperstep.py

@@ -0,0 +1,37 @@
+import os
+import pandas as pd
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def load_ip_data():
+    df = pd.read_csv(path("IP_DATA_ALL.csv"), header=0, low_memory=False,
+                     encoding="latin-1",
+                     usecols=["Country", "Place.Name", "Latitude", "Longitude"])
+    df.rename(columns={"Place.Name": "Place_Name"}, inplace=True)
+    return df
+
+
+def p3():
+    sFileName = path("IP_DATA_ALL.csv")
+    print("Loading :", sFileName)
+    IP_DATA_ALL = load_ip_data()
+
+    ROUTERLOC = IP_DATA_ALL.drop_duplicates(subset=None, keep="first",
+                                            inplace=False)
+    print("Rows :", ROUTERLOC.shape[0])
+    print("Columns :", ROUTERLOC.shape[1])
+
+    ROUTERLOC.to_csv(path("Retrieve_Router_Location.csv"), index=False)
+    print("### Done!! ############################################")
+
+
+if __name__ == "__main__":
+    p3()

nummpyy/structured.py

@@ -0,0 +1,58 @@
+import os
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+# Fallback to current working directory in interactive environments (like Colab) where __file__ is not defined
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p1a(image_name="1.png"):
+    from skimage import io
+
+    # Checking if the path exists, falling back to direct string if not absolute
+    img_path = path(image_name) if not os.path.isabs(image_name) else image_name
+    image = io.imread(img_path)
+    plt.imshow(image)
+    plt.title("Input Image")
+    plt.axis("off")
+    plt.show()
+
+    print("Image Shape :", image.shape)
+    print("Height :", image.shape[0])
+    print("Width :", image.shape[1])
+
+    if image.ndim == 2:  # grayscale -> make 3 channels
+        image = np.stack([image] * 3, axis=-1)
+
+    height, width, channels = image.shape
+    print("Color Mode :", "RGB" if channels == 3 else "RGBA")
+
+    ys, xs = np.indices((height, width))
+    r = image[:, :, 0].ravel()
+    g = image[:, :, 1].ravel()
+    b = image[:, :, 2].ravel()
+    a = image[:, :, 3].ravel() if channels == 4 else np.full(r.shape, 255)
+
+    df = pd.DataFrame({
+        "X": xs.ravel(), "Y": ys.ravel(),
+        "Red": r, "Green": g, "Blue": b, "Alpha": a
+    })
+
+    print(df.head(10))
+    print("\nRows :", df.shape[0])
+    print("Columns :", df.shape[1])
+
+    df.to_csv(path("Image_to_HORUS.csv"), index=False)
+    print("\nCSV File Saved Successfully.")
+
+
+if __name__ == "__main__":
+    p1a()

nummpyy/supervised.py

@@ -0,0 +1,68 @@
+import os
+import pandas as pd
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p12():
+    from sklearn.datasets import fetch_california_housing
+    from sklearn.model_selection import train_test_split
+    from sklearn.linear_model import LinearRegression
+    from sklearn.metrics import mean_squared_error, r2_score
+
+    try:
+        data = fetch_california_housing()  # needs internet the first time
+        X = pd.DataFrame(data.data, columns=data.feature_names)
+        y = data.target
+    except Exception:
+        # Offline fallback: use the dummy housing file next to this script
+        print("(No internet - using dummy_housing.csv instead)")
+        d = pd.read_csv(path("dummy_housing.csv"))
+        y = d["Price"].values
+        X = d.drop(columns=["Price"])
+
+    print("Dataset shape:", X.shape)
+    print("Features:", list(X.columns))
+
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size=0.2, random_state=42)
+    print("\nTraining samples:", X_train.shape[0])
+    print("Testing samples:", X_test.shape[0])
+
+    model = LinearRegression()
+    model.fit(X_train, y_train)
+    y_pred = model.predict(X_test)
+
+    print("\n========== Model Evaluation ==========")
+    print("Mean Squared Error (MSE):", mean_squared_error(y_test, y_pred))
+    print("R² Score:", r2_score(y_test, y_pred))
+
+    comparison = pd.DataFrame({"Actual Price": y_test,
+                               "Predicted Price": y_pred})
+    print("\n========== Actual vs Predicted ==========")
+    print(comparison.head(10))
+
+    plt.figure(figsize=(8, 6))
+    plt.scatter(y_test, y_pred, alpha=0.5)
+    lo = min(y_test.min(), y_pred.min())
+    hi = max(y_test.max(), y_pred.max())
+    plt.plot([lo, hi], [lo, hi], color="red", linewidth=2,
+             label="Perfect Prediction")
+    plt.xlabel("Actual Price")
+    plt.ylabel("Predicted Price")
+    plt.title("Actual vs Predicted Median House Values")
+    plt.legend()
+    plt.grid(True)
+    plt.show()
+
+
+if __name__ == "__main__":
+    p12()

nummpyy/thumbnail.py

@@ -0,0 +1,41 @@
+import os
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p11(image_name="1.png"):
+    from PIL import Image
+
+    nSize = 4
+    img = Image.open(path(image_name))
+
+    plt.figure(figsize=(nSize, nSize))
+    plt.title("Unchanged")
+    plt.imshow(img)
+    plt.show()
+
+    img.thumbnail((64, 64), Image.Resampling.LANCZOS)  # resizes in place
+
+    plt.figure(figsize=(nSize, nSize))
+    plt.title("Resized")
+    plt.imshow(img)
+    plt.show()
+
+    plt.figure(figsize=(nSize, nSize))
+    plt.title("Resized with Bi-Cubic")
+    plt.imshow(img, interpolation="bicubic")
+    plt.show()
+
+    print("### Done!! ###############################################")
+
+
+if __name__ == "__main__":
+    p11()

nummpyy/unsupervised.py

@@ -0,0 +1,109 @@
+import os
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p13():
+    import seaborn as sns
+    from sklearn.datasets import load_iris
+    from sklearn.preprocessing import StandardScaler
+    from sklearn.decomposition import PCA
+    from sklearn.cluster import KMeans
+    from sklearn.metrics import (adjusted_rand_score, silhouette_score,
+                                 confusion_matrix)
+
+    iris = load_iris()
+    X = pd.DataFrame(iris.data, columns=iris.feature_names)
+    y_true = iris.target
+    label_names = iris.target_names
+
+    print("Shape of feature data:", X.shape)
+    print(X.describe())
+
+    df_viz = X.copy()
+    df_viz["species"] = [label_names[i] for i in y_true]
+    sns.pairplot(df_viz, hue="species")
+    plt.show()
+
+    X_scaled = StandardScaler().fit_transform(X)
+
+    # Elbow method
+    inertia_values = []
+    k_range = range(1, 10)
+    for k in k_range:
+        km = KMeans(n_clusters=k, random_state=42, n_init=10)
+        km.fit(X_scaled)
+        inertia_values.append(km.inertia_)
+
+    plt.figure(figsize=(8, 5))
+    plt.plot(k_range, inertia_values, marker="o")
+    plt.xlabel("Number of Clusters (K)")
+    plt.ylabel("Inertia")
+    plt.title("Elbow Method to Find Optimal K")
+    plt.show()
+
+    # K-Means with K = 3
+    kmeans = KMeans(n_clusters=3, random_state=42, n_init=10)
+    cluster_labels = kmeans.fit_predict(X_scaled)
+
+    X["predicted_cluster"] = cluster_labels
+    X["actual_species"] = [label_names[i] for i in y_true]
+
+    # Map cluster numbers to real labels
+    mapping = {}
+    for cluster in np.unique(cluster_labels):
+        mask = cluster_labels == cluster
+        mapping[cluster] = pd.Series(y_true[mask]).mode()[0]
+
+    predicted_labels = np.array([mapping[c] for c in cluster_labels])
+    X["predicted_label_name"] = [label_names[i] for i in predicted_labels]
+    print(X[["actual_species", "predicted_cluster",
+             "predicted_label_name"]].head(10))
+
+    accuracy = (predicted_labels == y_true).mean()
+    print(f"Clustering-based label prediction accuracy: {accuracy * 100:.2f}%")
+    print(f"Adjusted Rand Index: {adjusted_rand_score(y_true, cluster_labels):.3f}")
+    print(f"Silhouette Score: {silhouette_score(X_scaled, cluster_labels):.3f}")
+
+    # Confusion matrix
+    cm = confusion_matrix(y_true, predicted_labels)
+    plt.figure(figsize=(6, 5))
+    sns.heatmap(cm, annot=True, fmt="d", cmap="Blues",
+                xticklabels=label_names, yticklabels=label_names)
+    plt.xlabel("Predicted Label (from clustering)")
+    plt.ylabel("Actual Label")
+    plt.title("Confusion Matrix: Clustering vs True Labels")
+    plt.show()
+
+    # PCA visualisation
+    X_pca = PCA(n_components=2).fit_transform(X_scaled)
+    plt.figure(figsize=(12, 5))
+
+    plt.subplot(1, 2, 1)
+    plt.scatter(X_pca[:, 0], X_pca[:, 1], c=cluster_labels, cmap="viridis")
+    plt.title("Predicted Clusters (K-Means)")
+    plt.xlabel("PCA Component 1")
+    plt.ylabel("PCA Component 2")
+
+    plt.subplot(1, 2, 2)
+    plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y_true, cmap="viridis")
+    plt.title("Actual Species (Ground Truth)")
+    plt.xlabel("PCA Component 1")
+    plt.ylabel("PCA Component 2")
+
+    plt.tight_layout()
+    plt.show()
+
+
+if __name__ == "__main__":
+    p13()

nummpyy/visualization.py

@@ -0,0 +1,86 @@
+import os
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+try:
+    BASE = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    BASE = os.getcwd()
+
+
+def path(name):
+    return os.path.join(BASE, name)
+
+
+def p5():
+    import matplotlib as ml
+    from pandas.plotting import (scatter_matrix, parallel_coordinates,
+                                 autocorrelation_plot)
+
+    # ---- Area plot ----
+    turnover = [2, 7, 14, 17, 20, 27, 30, 38, 25, 18, 6, 1]
+    plt.fill_between(np.arange(12), turnover, color="skyblue", alpha=0.4)
+    plt.plot(np.arange(12), turnover, color="Slateblue", alpha=0.6, linewidth=2)
+    plt.tick_params(labelsize=12)
+    plt.xticks(np.arange(12), np.arange(1, 13))
+    plt.xlabel("Month", size=12)
+    plt.ylabel("Turnover (K euros) of ice-cream", size=12)
+    plt.ylim(bottom=0)
+    plt.show()
+
+    # ---- Scatter plot ----
+    x = range(-10, 38, 1)
+    y = np.array(range(60, 770, 15)) + np.random.randn(48) * 40
+    plt.scatter(x, y, s=200, alpha=0.6)
+    plt.xlabel("Temperature (°C)", size=12)
+    plt.ylabel("Volume per store", size=12)
+    plt.show()
+
+    ml.style.use("ggplot")
+
+    # ---- KDE ----
+    plt.figure(figsize=(10, 10))
+    ser = pd.Series(np.random.randn(1000))
+    ser.plot(figsize=(10, 10), kind="kde")
+    plt.savefig(path("kde.png"), dpi=600)
+    plt.tight_layout()
+    plt.show()
+
+    # ---- Scatter matrix ----
+    df = pd.DataFrame(np.random.randn(1000, 5),
+                      columns=["Y2014", "Y2015", "Y2016", "Y2017", "Y2018"])
+    scatter_matrix(df, alpha=0.2, figsize=(10, 10), diagonal="kde")
+    plt.savefig(path("scatter_matrix.png"), dpi=600)
+    plt.tight_layout()
+    plt.show()
+
+    # ---- Parallel coordinates (iris1.csv, else built-in iris) ----
+    plt.figure(figsize=(10, 10))
+    if os.path.exists(path("iris1.csv")):
+        data = pd.read_csv(path("iris1.csv"))
+    else:
+        from sklearn.datasets import load_iris
+        iris = load_iris()
+        data = pd.DataFrame(iris.data, columns=["SepalLength", "SepalWidth",
+                                                "PetalLength", "PetalWidth"])
+        data["Name"] = [iris.target_names[i] for i in iris.target]
+    parallel_coordinates(data, "Name")
+    plt.savefig(path("parallel_coordinates.png"), dpi=600)
+    plt.tight_layout()
+    plt.show()
+
+    # ---- Autocorrelation plot ----
+    plt.figure(figsize=(10, 10))
+    data = pd.Series(0.7 * np.random.rand(1000) +
+                     0.3 * np.sin(np.linspace(-9 * np.pi, 9 * np.pi, num=1000)))
+    autocorrelation_plot(data)
+    plt.savefig(path("autocorrelation_plot.png"), dpi=600)
+    plt.tight_layout()
+    plt.show()
+
+    ml.style.use("default")
+
+
+if __name__ == "__main__":
+    p5()

nummpyy-1.0.0.dist-info/METADATA

@@ -0,0 +1,115 @@
+Metadata-Version: 2.4
+Name: nummpyy
+Version: 1.0.0
+Summary: Data Science practical programs, printable from Python or the terminal
+Home-page: 
+Author: andhrew
+Author-email: xyz@gmail.com
+License: MIT
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-python
+Dynamic: summary
+
+# nummpyy
+
+A Python package that stores **Data Science** practical programs and prints their source code on demand, from Python or the terminal.
+
+Install it once with `pip`, then view any practical on any machine without copying files around.
+
+---
+
+## Practicals included
+
+Pass any of these names (without `.py`) to `show_codes()` or the `nummpyy` command:
+
+| | | |
+|---|---|---|
+| `assesssuperstep` | `averagelatitude` | `correlation` |
+| `datascience` | `edges` | `extraspaces` |
+| `fixedlatitude` | `histogram` | `horus` |
+| `hough` | `multichannel` | `nlp` |
+| `reformatting` | `removing` | `retrievesuperstep` |
+| `structured` | `supervised` | `thumbnail` |
+| `unsupervised` | `visualization` | |
+
+The programs use `numpy`, `pandas` and `matplotlib`. Install those yourself if you want to run them; `nummpyy` only prints them.
+
+---
+
+## Install
+
+```bash
+pip install nummpyy
+```
+
+Upgrade:
+
+```bash
+pip install --upgrade nummpyy
+```
+
+Requires Python 3.6 or newer.
+
+---
+
+## View the programs
+
+### From the terminal
+
+```bash
+nummpyy                # show all practicals
+nummpyy correlation    # show one practical
+```
+
+### From Python
+
+```python
+import nummpyy
+
+nummpyy.show_codes()               # show all practicals
+nummpyy.show_codes("correlation")  # show one practical
+```
+
+### In Google Colab or Jupyter
+
+```python
+!pip install nummpyy
+import nummpyy
+nummpyy.show_codes("hough")
+```
+
+---
+
+## Publishing a new version (for maintainers)
+
+1. Add or update files in the `nummpyy/` folder.
+2. Increase `version` in `setup.py` (e.g. `1.0.1`). PyPI never accepts the same version twice.
+3. Clean old builds:
+   ```bash
+   rm -rf dist build *.egg-info
+   ```
+4. Build:
+   ```bash
+   python3 -m build
+   ```
+5. Upload to PyPI (username `__token__`, password is your `pypi-...` API token):
+   ```bash
+   python3 -m twine upload dist/*
+   ```
+
+---
+
+## License
+
+MIT. See [LICENSE](LICENSE).

nummpyy-1.0.0.dist-info/RECORD

@@ -0,0 +1,27 @@
+nummpyy/__init__.py,sha256=8G7C5aWV0Em38f0Mhaqwg-9n-zRlIS43r6OxNOC-zCA,1219
+nummpyy/assesssuperstep.py,sha256=40hrOqQRWdsMHRkBylQlr86ZHvTZYYgPc6Tybik5AQg,1254
+nummpyy/averagelatitude.py,sha256=GcrmunEJETzppEnDnTcUvxR08w2wQA1I0zvA-PkHVEg,740
+nummpyy/correlation.py,sha256=DfK2QZMXTOdUwnA8v0WcocpI83zq162RNl6s-ruf45Y,1035
+nummpyy/datascience.py,sha256=2FcXUDjfSbyB2rh82zOyKy3syxAF5SiUVZtQEY2pd3M,1424
+nummpyy/edges.py,sha256=sl05Uzxivd3r9wjAyz1NUUzo7AlPiGKr_3ueGkpZA2I,774
+nummpyy/extraspaces.py,sha256=rTPIaxgDrqx_1zG-aVRl0CuUNDhqZ7Mm-NfR_OVjhb8,395
+nummpyy/fixedlatitude.py,sha256=Mcoffh2T3Jmdpx0GKQOrTxsjWvbCgp6L9v1KYWRz1Gw,1148
+nummpyy/histogram.py,sha256=r7L0LV6lnA0wEqUYtMCO-XllC_j6K7gRfLKWkb3-mNg,1235
+nummpyy/horus.py,sha256=FYtrVufWafX0NM-AYHvTdkvYn0PWF2ljVDgkwvyArl0,926
+nummpyy/hough.py,sha256=IDzSQEw1yDabOq_qIgy6-4_yhm8etqqSVIfWxUsfgWg,1191
+nummpyy/multichannel.py,sha256=TBpIP353328ITBSwcbd8D7s4XbfDYbD01JfJgJqa_Vw,734
+nummpyy/nlp.py,sha256=BUxp2gywXiIfNPRMd7Q1nqOlJrQk239qop0pICH0A9A,1244
+nummpyy/reformatting.py,sha256=27t2MGcNXX8C-O3R0zLxP3VFOc2wHxQMRyaa1MY8gKA,493
+nummpyy/removing.py,sha256=0QUfnW2fcyhMB1BrcJx1yzSPpk-0dQGwxz4NNFX27z4,457
+nummpyy/retrievesuperstep.py,sha256=RUyoOVibz0p3Z2IIdGMJ8cCnAqnzntP68ivqXtvh4AQ,995
+nummpyy/structured.py,sha256=cIe7pF5GQl3V2OIhub2pRnNkY7cJ2SGGDf3o0mJvitI,1580
+nummpyy/supervised.py,sha256=o5Az8glQfn2932OpzzmIj_iC4jaNZVClI4FWdnjBrVc,2145
+nummpyy/thumbnail.py,sha256=xjWF-0MgVwwP0HEolpIEfMMzUGoEOzrekY631DAGGNY,836
+nummpyy/unsupervised.py,sha256=t9zMAGW2SgpGoSboVxVlxdqJYcyuBsY8T9qzFVVg8JE,3406
+nummpyy/visualization.py,sha256=FuPhep7BsGGrabiOhs9Bgq2Py7zCviaXtzS7ncmJvuU,2714
+nummpyy-1.0.0.dist-info/licenses/LICENSE,sha256=ZjOKHf0c1nYfvWea8C8w5Qxx-X-H4hBacrIZ_JDORRo,1075
+nummpyy-1.0.0.dist-info/METADATA,sha256=7-JgEnFx6HhQjAmWDvSmBlM1qYjOySDxPZUVO-GdvV4,2461
+nummpyy-1.0.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+nummpyy-1.0.0.dist-info/entry_points.txt,sha256=JGkVpI0VJ-6bn47AlOw1yDxOm5K5XigJjXtmiJBan5U,41
+nummpyy-1.0.0.dist-info/top_level.txt,sha256=7_s1FxniaU1yVUuwBNIm4j4HL1WUaIhJ-8vtjqIt48Q,8
+nummpyy-1.0.0.dist-info/RECORD,,

nummpyy-1.0.0.dist-info/WHEEL

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

nummpyy-1.0.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+nummpyy = nummpyy:main

nummpyy-1.0.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Chirag Vishwakarma
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

nummpyy-1.0.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+nummpyy