nummpyy 1.0.0__tar.gz

nummpyy-1.0.0/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/PKG-INFO

@@ -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/README.md

@@ -0,0 +1,92 @@
+# 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/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-1.0.0/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-1.0.0/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-1.0.0/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-1.0.0/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-1.0.0/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-1.0.0/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-1.0.0/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-1.0.0/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-1.0.0/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-1.0.0/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()