scypyy 0.7.0__tar.gz

scypyy-0.7.0/PKG-INFO

@@ -0,0 +1,32 @@
+Metadata-Version: 2.4
+Name: scypyy
+Version: 0.7.0
+Summary: A curated collection.
+License-Expression: MIT
+Project-URL: Homepage, https://google.com
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Dynamic: requires-python
+
+# scypyy
+
+A curated collection.
+## Installation
+
+```bash
+pip install scypyy
+```
+
+## Usage
+
+```python
+import scypyy
+
+print(scypyy.get())
+```
+
+This prints a help.

scypyy-0.7.0/README.md

@@ -0,0 +1,18 @@
+# scypyy
+
+A curated collection.
+## Installation
+
+```bash
+pip install scypyy
+```
+
+## Usage
+
+```python
+import scypyy
+
+print(scypyy.get())
+```
+
+This prints a help.

scypyy-0.7.0/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "scypyy"
+version = "0.7.0"
+description = "A curated collection."
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.8"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+    "Intended Audience :: Science/Research",
+    "Topic :: Scientific/Engineering",
+]
+
+[project.urls]
+Homepage = "https://google.com"

scypyy-0.7.0/scypyy/__init__.py

@@ -0,0 +1,5 @@
+"""scypyy - A curated collection of common Python imports for data science."""
+
+from .core import get
+
+__all__ = ["get"]

scypyy-0.7.0/scypyy/core.py

@@ -0,0 +1,1109 @@
+"""Core module containing curated import strings and code templates by topic."""
+
+
+class _Get:
+    """Namespace for categorized import and code helpers."""
+
+    def libs(self):
+        """All commonly used imports for data science, ML, stats, and visualization."""
+        print("""\
+import numpy as np
+import pandas as pd
+
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+from scipy import stats
+from scipy.stats import norm                  # Z-test (normal distribution)
+from scipy.stats import t                     # t-test (t-distribution)
+from scipy.stats import binom                 # binomial distribution
+from scipy.stats import poisson               # poisson distribution
+from scipy.stats import bernoulli             # bernoulli distribution
+from scipy.optimize import minimize           # optimization
+from scipy.special import factorial           # factorial function
+from numpy import maximum                     # element-wise max
+
+from statistics import stdev                  # sample standard deviation
+
+import statsmodels.api as sm
+import statsmodels.formula.api as smf         # smf.ols(), smf.logit()
+from statsmodels.formula.api import ols       # for ANOVA
+from statsmodels.stats.proportion import proportions_ztest  # proportion z-test
+from statsmodels.stats.outliers_influence import variance_inflation_factor  # VIF
+from statsmodels.tools.tools import add_constant
+import statsmodels.stats.multicomp as mc      # multiple comparison (Tukey)
+from statsmodels.multivariate.manova import MANOVA  # MANOVA
+
+import sklearn.linear_model as lm
+from sklearn.linear_model import LinearRegression
+from sklearn.linear_model import Ridge, RidgeCV
+from sklearn.linear_model import Lasso, LassoCV
+from sklearn.linear_model import LogisticRegression
+
+from sklearn import preprocessing
+from sklearn.preprocessing import scale
+from sklearn.preprocessing import StandardScaler
+from sklearn.preprocessing import LabelEncoder
+from sklearn.preprocessing import OneHotEncoder
+
+from sklearn.model_selection import train_test_split
+from sklearn.model_selection import KFold
+from sklearn.model_selection import cross_val_score
+
+from sklearn.metrics import mean_squared_error
+from sklearn.metrics import confusion_matrix
+from sklearn.metrics import accuracy_score
+
+df = sns.load_dataset('dataset_Asked')""")
+
+    def hypothesis(self):
+        """Hypothesis testing — all test types with examples."""
+        print("""\
+## ============================================================
+## ALL HYPOTHESIS TESTING CODES - LAB 4 TO LAB 7
+## ============================================================
+
+import numpy as np
+from scipy import stats
+from scipy.stats import norm
+from scipy.stats import t
+from statistics import stdev
+from statsmodels.stats.proportion import proportions_ztest
+
+
+## ============================================================
+## 1. ONE-SAMPLE Z-TEST (TWO-SIDED)
+##    Population SD (sigma) KNOWN
+##    Keywords: "differ", "same", "equal", "changed"
+## ============================================================
+
+mu = 84
+xbar = 81.5
+sigma = 10
+n = 75
+alpha = 0.01
+
+se = sigma / np.sqrt(n)
+Z_cal = (xbar - mu) / se
+
+Z_pos = norm.ppf(1 - alpha/2)
+Z_neg = norm.ppf(alpha/2)
+
+print("=== 1. One-Sample Z-Test (Two-Sided) ===")
+print(f"Z_cal = {Z_cal}")
+print(f"Z_table = [{Z_neg}, {Z_pos}]")
+print(f"p-value = {norm.cdf(Z_cal)}")
+print(f"CI = [{mu + Z_neg * se}, {mu + Z_pos * se}]")
+# Accept H0 if |Z_cal| < |Z_table|
+# Accept H0 if p-value > alpha
+# Accept H0 if xbar inside CI
+
+
+## ============================================================
+## 2. ONE-SAMPLE Z-TEST (ONE-SIDED LEFT)
+##    Keywords: "less", "lower", "decreased"
+## ============================================================
+
+mu = 14500
+xbar = 13000
+sigma = 2100
+n = 25
+alpha = 0.01
+
+se = sigma / np.sqrt(n)
+Z_cal = (xbar - mu) / se
+
+Z_neg = norm.ppf(alpha)
+
+print("=== 2. One-Sample Z-Test (One-Sided Left) ===")
+print(f"Z_cal = {Z_cal}")
+print(f"Z_neg = {Z_neg}")
+print(f"p-value = {norm.cdf(Z_cal)}")
+print(f"Boundary = {mu + Z_neg * se}")
+# Reject H0 if Z_cal < Z_neg
+# Reject H0 if p-value < alpha
+# Reject H0 if xbar < boundary
+
+
+## ============================================================
+## 3. ONE-SAMPLE Z-TEST (ONE-SIDED RIGHT)
+##    Keywords: "greater", "higher", "increased"
+## ============================================================
+
+mu = 50
+xbar = 55
+sigma = 10
+n = 36
+alpha = 0.05
+
+se = sigma / np.sqrt(n)
+Z_cal = (xbar - mu) / se
+
+Z_pos = norm.ppf(1 - alpha)
+
+print("=== 3. One-Sample Z-Test (One-Sided Right) ===")
+print(f"Z_cal = {Z_cal}")
+print(f"Z_pos = {Z_pos}")
+print(f"p-value = {1 - norm.cdf(Z_cal)}")
+print(f"Boundary = {mu + Z_pos * se}")
+# Reject H0 if Z_cal > Z_pos
+# Reject H0 if p-value < alpha
+# Reject H0 if xbar > boundary
+
+
+## ============================================================
+## 4. ONE-SAMPLE t-TEST (TWO-SIDED)
+##    Population SD UNKNOWN, use sample SD
+##    Keywords: "differ", "same", "equal"
+## ============================================================
+
+mu = 100
+xbar = 95.8
+s = 17.5
+n = 100
+df = n - 1
+alpha = 0.05
+
+se = s / np.sqrt(n)
+t_cal = (xbar - mu) / se
+
+t_pos = t.ppf(1 - alpha/2, df)
+t_neg = t.ppf(alpha/2, df)
+
+print("=== 4. One-Sample t-Test (Two-Sided) ===")
+print(f"t_cal = {t_cal}")
+print(f"t_table = [{t_neg}, {t_pos}]")
+print(f"p-value = {t.cdf(t_cal, df) * 2}")
+print(f"CI = [{mu + t_neg * se}, {mu + t_pos * se}]")
+# Reject H0 if |t_cal| > |t_table|
+# Reject H0 if p-value < alpha
+# Reject H0 if xbar outside CI
+
+
+## ============================================================
+## 5. ONE-SAMPLE t-TEST (ONE-SIDED LEFT)
+##    Keywords: "less", "lower", "decreased"
+## ============================================================
+
+mu = 100
+xbar = 95.8
+s = 17.5
+n = 100
+df = n - 1
+alpha = 0.05
+
+se = s / np.sqrt(n)
+t_cal = (xbar - mu) / se
+
+t_neg = t.ppf(alpha, df)
+
+print("=== 5. One-Sample t-Test (One-Sided Left) ===")
+print(f"t_cal = {t_cal}")
+print(f"t_neg = {t_neg}")
+print(f"p-value = {t.cdf(t_cal, df)}")
+print(f"Boundary = {mu + t_neg * se}")
+# Reject H0 if t_cal < t_neg
+# Reject H0 if p-value < alpha
+# Reject H0 if xbar < boundary
+
+
+## ============================================================
+## 6. ONE-SAMPLE t-TEST (ONE-SIDED RIGHT)
+##    Keywords: "greater", "higher", "increased"
+## ============================================================
+
+mu = 100
+xbar = 105
+s = 17.5
+n = 100
+df = n - 1
+alpha = 0.05
+
+se = s / np.sqrt(n)
+t_cal = (xbar - mu) / se
+
+t_pos = t.ppf(1 - alpha, df)
+
+print("=== 6. One-Sample t-Test (One-Sided Right) ===")
+print(f"t_cal = {t_cal}")
+print(f"t_pos = {t_pos}")
+print(f"p-value = {1 - t.cdf(t_cal, df)}")
+print(f"Boundary = {mu + t_pos * se}")
+# Reject H0 if t_cal > t_pos
+# Reject H0 if p-value < alpha
+# Reject H0 if xbar > boundary
+
+
+## ============================================================
+## 7. ONE-SAMPLE t-TEST USING BUILT-IN (ttest_1samp)
+##    When you have RAW DATA (not xbar and s)
+## ============================================================
+
+X = np.array([10, 12, 13, 14, 15, 2, 7, 8])
+
+print("=== 7. ttest_1samp (Built-in) ===")
+print("Two-sided:", stats.ttest_1samp(X, popmean=12, alternative='two-sided'))
+print("Left:     ", stats.ttest_1samp(X, popmean=12, alternative='less'))
+print("Right:    ", stats.ttest_1samp(X, popmean=12, alternative='greater'))
+# Reject H0 if pvalue < alpha
+
+
+## ============================================================
+## 8. ONE-SAMPLE PROPORTION Z-TEST (TWO-SIDED)
+##    Keywords: "differ", "same", "equal"
+## ============================================================
+
+p = 0.15
+pbar = 22 / 120
+n = 120
+alpha = 0.02
+
+se = np.sqrt((p * (1 - p)) / n)
+Z_cal = (pbar - p) / se
+
+Z_pos = norm.ppf(1 - alpha/2)
+Z_neg = norm.ppf(alpha/2)
+
+print("=== 8. One-Sample Proportion Z-Test (Two-Sided) ===")
+print(f"Z_cal = {Z_cal}")
+print(f"Z_table = [{Z_neg}, {Z_pos}]")
+print(f"p-value = {norm.cdf(Z_cal)}")
+print(f"CI = [{p + Z_neg * se}, {p + Z_pos * se}]")
+# Accept H0 if |Z_cal| < |Z_table|
+# Accept H0 if p-value > alpha
+# Accept H0 if pbar inside CI
+
+
+## ============================================================
+## 9. ONE-SAMPLE PROPORTION Z-TEST (ONE-SIDED RIGHT)
+##    Keywords: "increased", "greater", "more"
+## ============================================================
+
+p = 0.05
+pbar = 335 / 6000
+n = 6000
+alpha = 0.02
+
+se = np.sqrt((p * (1 - p)) / n)
+Z_cal = (pbar - p) / se
+
+Z_pos = norm.ppf(1 - alpha)
+
+print("=== 9. One-Sample Proportion Z-Test (One-Sided Right) ===")
+print(f"Z_cal = {Z_cal}")
+print(f"Z_pos = {Z_pos}")
+print(f"p-value = {1 - norm.cdf(Z_cal)}")
+print(f"Boundary = {p + Z_pos * se}")
+# Reject H0 if Z_cal > Z_pos
+# Reject H0 if p-value < alpha
+# Reject H0 if pbar > boundary
+
+
+## ============================================================
+## 10. ONE-SAMPLE PROPORTION USING BUILT-IN (proportions_ztest)
+## ============================================================
+
+print("=== 10. proportions_ztest (Built-in) ===")
+print("Two-sided:", proportions_ztest(count=22, nobs=120, value=0.15, alternative='two-sided'))
+print("Right:    ", proportions_ztest(count=335, nobs=6000, value=0.05, alternative='larger'))
+print("Left:     ", proportions_ztest(count=22, nobs=120, value=0.15, alternative='smaller'))
+# alternative: 'two-sided', 'smaller', 'larger'
+# Reject H0 if pvalue < alpha
+
+
+## ============================================================
+## 11. TWO-SAMPLE Z-TEST FOR MEANS (TWO-SIDED)
+##     Both sigma known
+##     Keywords: "differ", "same", "equal"
+## ============================================================
+
+xbar1, xbar2 = 86, 82
+sigma1, sigma2 = 6, 9
+n1, n2 = 60, 75
+alpha = 0.01
+
+se = np.sqrt(sigma1**2/n1 + sigma2**2/n2)
+Z_cal = ((xbar1 - xbar2) - 0) / se
+
+Z_pos = norm.ppf(1 - alpha/2)
+Z_neg = norm.ppf(alpha/2)
+
+print("=== 11. Two-Sample Z-Test Means (Two-Sided) ===")
+print(f"Z_cal = {Z_cal}")
+print(f"Z_table = [{Z_neg}, {Z_pos}]")
+print(f"p-value = {(1 - norm.cdf(Z_cal)) * 2}")
+print(f"CI = [{0 + Z_neg * se}, {0 + Z_pos * se}]")
+# Reject H0 if |Z_cal| > |Z_table|
+# Reject H0 if p-value < alpha
+# Reject H0 if (xbar1-xbar2) outside CI
+
+
+## ============================================================
+## 12. TWO-SAMPLE Z-TEST FOR MEANS (ONE-SIDED RIGHT)
+##     Keywords: "greater", "higher", "increased"
+## ============================================================
+
+xbar1, xbar2 = 13.8, 9.1
+sigma1, sigma2 = 18.9, 8.7
+n1, n2 = 41, 35
+alpha = 0.10
+
+se = np.sqrt(sigma1**2/n1 + sigma2**2/n2)
+Z_cal = ((xbar1 - xbar2) - 0) / se
+
+Z_pos = norm.ppf(1 - alpha)
+
+print("=== 12. Two-Sample Z-Test Means (One-Sided Right) ===")
+print(f"Z_cal = {Z_cal}")
+print(f"Z_pos = {Z_pos}")
+print(f"p-value = {1 - norm.cdf(Z_cal)}")
+print(f"Boundary = {0 + Z_pos * se}")
+# Reject H0 if Z_cal > Z_pos
+# Reject H0 if p-value < alpha
+# Reject H0 if (xbar1-xbar2) > boundary
+
+
+## ============================================================
+## 13. TWO-SAMPLE t-TEST EQUAL VARIANCE (TWO-SIDED)
+##     sigma unknown, use pooled SD
+##     Keywords: "differ", "same", "equal"
+## ============================================================
+
+X = np.array([10, 12, 13, 14, 15, 2, 7, 8])
+# Using built-in
+print("=== 13. Two-Sample t-Test Equal Var (Built-in) ===")
+a = np.array([56, 128.6, 12, 123.8, 64.34, 78, 763.3])
+b = np.array([1.1, 2.9, 4.2])
+print("Equal var: ", stats.ttest_ind(a, b, equal_var=True, alternative='two-sided'))
+print("Unequal var:", stats.ttest_ind(a, b, equal_var=False, alternative='two-sided'))
+# Reject H0 if pvalue < alpha
+
+
+## ============================================================
+## 14. TWO-SAMPLE t-TEST EQUAL VARIANCE (MANUAL - ONE-SIDED)
+##     Pooled SD formula
+## ============================================================
+
+Bus = np.array([2.86, 2.77, 3.18, 2.80, 3.14, 2.87, 3.19, 3.24, 2.91, 3, 2.83])
+As = np.array([3.35, 3.32, 3.36, 3.63, 3.41, 3.37, 3.45, 3.43, 3.44, 3.17, 3.26, 3.18, 3.41])
+
+xbar1 = np.mean(Bus)
+xbar2 = np.mean(As)
+s1 = stdev(Bus)
+s2 = stdev(As)
+n1 = len(Bus)
+n2 = len(As)
+alpha = 0.02
+hypothesized_diff = -0.25
+
+# Pooled SD
+sp = np.sqrt(((n1-1)*s1**2 + (n2-1)*s2**2) / (n1 + n2 - 2))
+se = sp * np.sqrt(1/n1 + 1/n2)
+df = n1 + n2 - 2
+
+t_cal = ((xbar1 - xbar2) - hypothesized_diff) / se
+t_neg = t.ppf(alpha, df)
+
+print("=== 14. Two-Sample t-Test Pooled (One-Sided Left) ===")
+print(f"Pooled SD = {sp}")
+print(f"SE = {se}")
+print(f"t_cal = {t_cal}")
+print(f"t_neg = {t_neg}")
+print(f"df = {df}")
+print(f"p-value = {t.cdf(t_cal, df)}")
+print(f"Boundary = {hypothesized_diff + t_neg * se}")
+# Reject H0 if t_cal < t_neg
+# Reject H0 if p-value < alpha
+
+
+## ============================================================
+## 15. TWO-SAMPLE t-TEST UNEQUAL VARIANCE (MANUAL - ONE-SIDED)
+## ============================================================
+
+xbar1, xbar2 = 27.2, 32.4
+s1, s2 = 3.8, 4.3
+n1, n2 = 12, 9
+alpha = 0.01
+
+sp = np.sqrt(((n1-1)*s1**2 + (n2-1)*s2**2) / (n1 + n2 - 2))
+se = sp * np.sqrt(1/n1 + 1/n2)
+df = n1 + n2 - 2
+
+t_cal = ((xbar1 - xbar2) - 0) / se
+t_neg = t.ppf(alpha, df)
+
+print("=== 15. Two-Sample t-Test Unequal Var (One-Sided Left) ===")
+print(f"t_cal = {t_cal}")
+print(f"t_neg = {t_neg}")
+print(f"p-value = {t.cdf(t_cal, df)}")
+print(f"Boundary = {0 + t_neg * se}")
+# Reject H0 if t_cal < t_neg
+# Reject H0 if p-value < alpha
+
+
+## ============================================================
+## 16. TWO-SAMPLE t-TEST USING BUILT-IN (ttest_ind)
+## ============================================================
+
+a = np.array([56, 128.6, 12, 123.8, 64.34, 78, 763.3])
+b = np.array([1.1, 2.9, 4.2])
+
+print("=== 16. ttest_ind (Built-in) ===")
+print("Two-sided equal:  ", stats.ttest_ind(a, b, equal_var=True, alternative='two-sided'))
+print("Two-sided unequal:", stats.ttest_ind(a, b, equal_var=False, alternative='two-sided'))
+print("Left equal:       ", stats.ttest_ind(a, b, equal_var=True, alternative='less'))
+print("Right equal:      ", stats.ttest_ind(a, b, equal_var=True, alternative='greater'))
+# equal_var=True  --> pooled (df = n1+n2-2)
+# equal_var=False --> Welch's (fractional df)
+# alternative: 'two-sided', 'less', 'greater'
+# Reject H0 if pvalue < alpha
+
+
+## ============================================================
+## 17. TWO-SAMPLE PROPORTION Z-TEST (ONE-SIDED LEFT)
+##     Keywords: "increased" but p1(old) - p2(new) < 0
+## ============================================================
+
+n1, n2 = 400, 380
+p1 = 166 / 400
+p2 = 205 / 380
+alpha = 0.01
+
+phat = (n1*p1 + n2*p2) / (n1 + n2)
+se = np.sqrt(phat * (1 - phat) * (1/n1 + 1/n2))
+Z_cal = ((p1 - p2) - 0) / se
+
+Z_neg = norm.ppf(alpha)
+
+print("=== 17. Two-Sample Proportion Z-Test (One-Sided Left) ===")
+print(f"Pooled proportion = {phat}")
+print(f"Z_cal = {Z_cal}")
+print(f"Z_neg = {Z_neg}")
+print(f"p-value = {norm.cdf(Z_cal)}")
+print(f"Boundary = {0 + Z_neg * se}")
+# Reject H0 if Z_cal < Z_neg
+# Reject H0 if p-value < alpha
+# Reject H0 if (p1-p2) < boundary
+
+
+## ============================================================
+## 18. TWO-SAMPLE PROPORTION USING BUILT-IN (proportions_ztest)
+## ============================================================
+
+count = np.array([166, 205])
+nobs = np.array([400, 380])
+
+print("=== 18. Two-Sample proportions_ztest (Built-in) ===")
+stat, pval = proportions_ztest(count, nobs)
+print(f"Two-sided: stat={stat:.4f}, pval={pval:.4f}")
+# Reject H0 if pval < alpha
+
+
+## ============================================================
+## 19. PAIRED t-TEST (DEPENDENT SAMPLES) - MANUAL
+##     Same subjects measured twice (before/after)
+## ============================================================
+
+a = np.array([56, 128, 12, 123, 64, 78, 763])
+b = np.array([46, 100, 5, 121, 54, 80, 700])
+
+c = a - b
+xbar = np.mean(c)
+sample_sd = stdev(c)
+n = len(c)
+df = n - 1
+alpha = 0.05
+
+se = sample_sd / np.sqrt(n)
+t_cal = (xbar - 0) / se
+
+t_pos = t.ppf(1 - alpha/2, df)
+t_neg = t.ppf(alpha/2, df)
+
+print("=== 19. Paired t-Test Manual (Two-Sided) ===")
+print(f"Differences = {list(c)}")
+print(f"Mean diff = {xbar}")
+print(f"t_cal = {t_cal}")
+print(f"t_table = [{t_neg}, {t_pos}]")
+print(f"p-value = {(1 - t.cdf(t_cal, df)) * 2}")
+# Accept H0 if |t_cal| < |t_table|
+# Accept H0 if p-value > alpha
+
+
+## ============================================================
+## 20. PAIRED t-TEST USING BUILT-IN (ttest_rel)
+## ============================================================
+
+a = np.array([56, 128, 12, 123, 64, 78, 763])
+b = np.array([46, 100, 5, 121, 54, 80, 700])
+
+print("=== 20. ttest_rel (Built-in) ===")
+print("Two-sided:", stats.ttest_rel(a, b, alternative='two-sided'))
+print("Greater:  ", stats.ttest_rel(a, b, alternative='greater'))
+print("Less:     ", stats.ttest_rel(a, b, alternative='less'))
+# alternative: 'two-sided', 'less', 'greater'
+# Reject H0 if pvalue < alpha""")
+
+    def mle(self):
+        """Maximum likelihood estimation — Normal, Binomial, Poisson."""
+        print("""\
+import numpy as np
+from scipy.stats import norm, poisson
+from scipy.optimize import minimize
+from math import factorial
+
+
+## ============================================================
+## 1. MLE - NORMAL DISTRIBUTION
+## ============================================================
+
+def normal_dist(params,data):
+    mu, sd = params
+    log1 = norm.logpdf(data, mu, sd)
+    lll = -np.sum(log1)
+    return lll
+
+initial_guess = [10, 3]
+result = minimize(nll, initial_guess, args=(data,), bounds=((None, None), (1e-5, None)))
+print("mean", result.x[0])
+print("sd", result.x[1])
+
+
+## ============================================================
+## 2. MLE - BINOMIAL DISTRIBUTION
+## ============================================================
+
+hospital_data = [
+    (100, 85),
+    (150, 120),
+    (200, 160),
+    (250, 210),
+    (300, 260)
+]
+
+inta = [0.1]
+def binomial_dist(p,n,k):
+    a1=factorial(n)/((factorial(n-k)*factorial(k)))
+    a2=(p**k)*((1-p)**(n-k))
+    ll = a1*a2
+    logll = np.log(ll)
+    return -logll
+for n, k in hospital_data:
+    result = minimize(BLL, inta, args=(n,k), bounds=[(0.00005, 0.99995)])
+    print("prob", result.x[0])
+
+
+## ============================================================
+## 3. MLE - POISSON DISTRIBUTION
+## ============================================================
+
+def poisson_dist(lam, x):
+    log=[]
+    for i in x:
+        logs = np.log(poisson.pmf(x[i], lam))
+        log.append(logs)
+    return np.sum(log)
+lams = np.arange(0,12,1)
+ls = []
+for lam in lams:
+    lsa = pd(lam, data)
+    ls.append(lsa)
+bestll = lams[np.argmax(ls)]
+print(bestll)""")
+
+    def nonpara(self):
+        """Non-parametric tests — Mann-Whitney U, Kruskal-Wallis, Sign test."""
+        print("""\
+import numpy as np
+from scipy.stats import mannwhitneyu
+from scipy import stats
+
+
+## ============================================================
+## 1. MANN-WHITNEY U TEST
+## ============================================================
+
+a=np.array([])
+b=np.array([])
+u_stat,p_value=mannwhitneyu(a,b,alternative="")
+
+
+## ============================================================
+## 2. KRUSKAL-WALLIS H TEST
+## ============================================================
+
+a=np.array([])
+b=np.array([])
+results=stats.kruskal(a,b)
+
+
+## ============================================================
+## 3. SIGN TEST
+## ============================================================
+
+from statsmodels.stats.descriptivestats import sign_test
+a=np.array([])
+b=np.array([])
+diff=a-b
+stat_val,p_val=sign_test(diff)""")
+
+    def linearregression(self):
+        """Simple linear regression — sklearn, OLS summary, VIF, prediction, train-test."""
+        print("""\
+import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import (train_test_split,KFold,cross_val_score)
+import statsmodels.formula.api as smf
+from statsmodels.stats.outliers_influence import (variance_inflation_factor)
+import statsmodels.api as sm
+
+df = pd.read_csv('data.csv')
+print(df.head())
+print(df.info())
+print(df.corr())
+# Regplot
+sns.regplot(x='FV1',y='targetvariable',data=df)
+plt.show()
+
+# SIMPLE LINEAR REGRESSION
+lr = LinearRegression()
+X = df['FV1'].values.reshape(-1,1)
+Y = df['targetvariable']
+
+#VIF
+X_vif = pd.DataFrame(X,columns=['FV1'])
+X_vif = sm.add_constant(X_vif)
+vif = pd.DataFrame()
+vif["Feature"] = X_vif.columns
+vif["VIF"] = [variance_inflation_factor(X_vif.values,i)
+    for i in range(X_vif.shape[1])]
+print(vif)
+
+lr.fit(X,Y)
+print("Intercept =", lr.intercept_)
+print("Coefficient =", lr.coef_)
+print(f"Equation: targetvariable = "f"{lr.intercept_:.4f} + "f"{lr.coef_[0]:.4f} * FV1")
+
+# RSS
+RSS = np.sum((lr.intercept_ +lr.coef_ * X -Y.values.reshape(-1,1))**2)
+print("RSS =", RSS)
+
+# SUMMARY
+lm_fit = smf.ols('targetvariable ~ FV1',df).fit()
+print(lm_fit.summary())
+
+# PREDICTION
+predictions = lm_fit.predict(pd.DataFrame({'FV1':[5,10,15]}))
+print(predictions)
+
+# TRAIN TEST SPLIT
+X_train, X_test, Y_train, Y_test = train_test_split(X,Y,test_size=0.20,random_state=123)
+
+lr.fit(X_train,Y_train)
+pred_test = lr.predict(X_test)
+
+# TEST MSE
+mse_test = np.mean((Y_test - pred_test)**2)
+print("Test MSE =", mse_test)
+print("R-Squared =", lm_fit.rsquared)""")
+
+    def multilr(self):
+        """Multiple linear regression — sklearn, OLS, interaction, VIF, scaling, K-Fold."""
+        print("""\
+# MULTIPLE LINEAR REGRESSION
+import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+from sklearn.linear_model import LinearRegression
+from sklearn.model_selection import (train_test_split,KFold,cross_val_score)
+from sklearn.preprocessing import StandardScaler
+import statsmodels.formula.api as smf
+from statsmodels.stats.outliers_influence import (variance_inflation_factor)
+import statsmodels.api as sm
+
+df = pd.read_csv('data.csv')
+print(df.head())
+print(df.info())
+print(df.corr())
+
+sns.regplot(x='FV1',y='targetvariable',data=df)
+plt.show()
+sns.regplot(x='FV2',y='targetvariable',data=df)
+plt.show()
+sns.regplot(x='FV3',y='targetvariable',data=df)
+plt.show()
+
+X = df[['FV1','FV2','FV3']]
+Y = df['targetvariable']
+
+X_vif = sm.add_constant(X)
+vif = pd.DataFrame()
+vif["Feature"] = X_vif.columns
+vif["VIF"] = [variance_inflation_factor(X_vif.values,i)
+    for i in range(X_vif.shape[1])]
+print(vif)
+
+X_train, X_test, Y_train, Y_test = train_test_split(X,Y,test_size=0.20,random_state=123)
+lr = LinearRegression()
+lr.fit(X_train,Y_train)
+print("Intercept =", lr.intercept_)
+print("Coefficients =", lr.coef_)
+pred_test = lr.predict(X_test)
+print(pred_test)
+mse = np.mean((Y_test - pred_test)**2)
+print("MSE =", mse)
+r2_score = lr.score(X_test,Y_test)
+print("R-Squared =", r2_score)
+
+#1
+lm_fit = smf.ols('targetvariable ~ FV1 + FV2 + FV3',df).fit()
+print(lm_fit.summary())
+print("R-Squared =", lm_fit.rsquared)
+#2
+lm_fit2 = smf.ols('targetvariable ~ FV1 * FV2',df).fit()
+print(lm_fit2.summary())
+print("R-Squared =", lm_fit.rsquared)
+
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+model = LinearRegression()
+kfold = KFold(10,random_state=0,shuffle=True)
+mse_cv = cross_val_score(model,X,Y,cv=kfold,scoring='neg_mean_squared_error')
+print("Average MSE =", np.mean(-mse_cv))
+r2_cv = cross_val_score(model,X,Y,cv=kfold,scoring='r2')
+print("R2 Score Per Fold =")
+print(r2_cv)
+print("Average Accuracy (R2 Score) =",np.mean(r2_cv))""")
+
+    def ridge(self):
+        """Ridge regression — with CV and train-test split."""
+        print("""\
+import pandas as pd
+import numpy as np
+from sklearn.linear_model import (Ridge,RidgeCV)
+
+from sklearn.model_selection import (train_test_split)
+
+from sklearn.metrics import (mean_squared_error)
+
+from sklearn.preprocessing import (StandardScaler)
+
+df = pd.read_csv('data.csv')
+print(df.head())
+print(df.info())
+print(df.corr())
+
+X = df[['FV1','FV2','FV3','FV4']]
+Y = df['targetvariable']
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+
+X_train, X_test, Y_train, Y_test = train_test_split(X_scaled,Y,test_size=0.20,random_state=123)
+ridge = Ridge(alpha=10)
+ridge.fit(X_train,Y_train)
+
+print("Ridge Coefficients =")
+print(pd.Series(ridge.coef_,index=X.columns))
+
+pred = ridge.predict(X_test)
+print(pred)
+
+mse = mean_squared_error(Y_test,pred)
+print("Test MSE =", mse)
+
+r2 = ridge.score(X_test,Y_test)
+print("R-Squared =", r2)
+
+alphas = 10 ** np.linspace(10,-2,100) * 0.5
+
+ridgecv = RidgeCV(alphas=alphas)
+
+ridgecv.fit(X_scaled,Y)
+
+print("Best Alpha =",ridgecv.alpha_)
+ridge_best = Ridge(alpha=ridgecv.alpha_)
+
+ridge_best.fit(X_train,Y_train)
+pred_best = ridge_best.predict(X_test)
+
+mse_best = mean_squared_error(Y_test,pred_best)
+
+print("Best Model Test MSE =",mse_best)
+r2_best = ridge_best.score(X_test,Y_test)
+
+print("Best Model R-Squared =",r2_best)""")
+
+    def lasso(self):
+        """Lasso regression — with LassoCV and train-test split."""
+        print("""\
+import pandas as pd
+import numpy as np
+
+from sklearn.linear_model import (Lasso,LassoCV)
+from sklearn.model_selection import (train_test_split)
+from sklearn.metrics import (
+mean_squared_error)
+from sklearn.preprocessing import (StandardScaler)
+
+df = pd.read_csv('data.csv')
+print(df.head())
+print(df.info())
+print(df.corr())
+
+X = df[['FV1','FV2','FV3','FV4']]
+Y = df['targetvariable']
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+X_train, X_test, Y_train, Y_test = train_test_split(X_scaled,Y,test_size=0.20,random_state=123)
+lasso = Lasso(alpha=10)
+lasso.fit(X_train,Y_train)
+
+print("Lasso Coefficients =")
+print(pd.Series(lasso.coef_,index=X.columns))
+
+print("Notice: Lasso may set some coefficients to EXACTLY 0")
+pred_lasso = lasso.predict(X_test)
+print(pred_lasso)
+mse = mean_squared_error(Y_test,pred_lasso)
+print("Test MSE =", mse)
+r2 = lasso.score(X_test,Y_test)
+print("R-Squared =", r2)
+
+alphas = 10 ** np.linspace(10,-2,100) * 0.5
+lassocv = LassoCV(alphas=alphas)
+lassocv.fit(X_train,Y_train)
+print("Best Alpha =",lassocv.alpha_)
+lasso_best = Lasso(alpha=lassocv.alpha_)
+
+lasso_best.fit(X_train,Y_train)
+pred_lasso_best = lasso_best.predict(X_test)
+print("Lasso Best Model Coefficients =")
+print(pd.Series(lasso_best.coef_,index=X.columns))
+mse_best = mean_squared_error(Y_test,pred_lasso_best)
+print("Best Model Test MSE =",mse_best)
+r2_best = lasso_best.score(X_test,Y_test)
+print("Best Model R-Squared =",r2_best)""")
+
+    def ridgelasso(self):
+        """Combined Ridge, Lasso, Linear Regression with VIF, OLS, and K-Fold."""
+        print("""\
+import pandas as pd
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+from sklearn.linear_model import (LinearRegression,Ridge,RidgeCV,Lasso,LassoCV)
+from sklearn.model_selection import (train_test_split,KFold,cross_val_score)
+from sklearn.metrics import (mean_squared_error)
+from sklearn.preprocessing import (StandardScaler)
+import statsmodels.formula.api as smf
+from statsmodels.stats.outliers_influence import (variance_inflation_factor)
+import statsmodels.api as sm
+df = pd.read_csv('data.csv')
+print(df.head())
+print(df.info())
+print(df.corr())
+
+sns.regplot(x='FV1',y='targetvariable',data=df)
+plt.show()
+sns.regplot(x='FV2',y='targetvariable',data=df)
+plt.show()
+sns.regplot(x='FV3',y='targetvariable',data=df)
+plt.show()
+
+X = df[['FV1','FV2','FV3','FV4']]
+Y = df['targetvariable']
+
+X_vif = sm.add_constant(X)
+vif = pd.DataFrame()
+vif["Feature"] = X_vif.columns
+vif["VIF"] = [variance_inflation_factor(X_vif.values,i)
+    for i in range(X_vif.shape[1])]
+print(vif)
+
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+X_train, X_test, Y_train, Y_test = train_test_split(X_scaled,Y,test_size=0.20,random_state=123)
+lr = LinearRegression()
+lr.fit(X_train,Y_train)
+print("Intercept =", lr.intercept_)
+print("Coefficients =")
+print(pd.Series(lr.coef_,index=X.columns))
+pred_lr = lr.predict(X_test)
+mse_lr = mean_squared_error(Y_test,pred_lr)
+print("Linear Regression MSE =", mse_lr)
+r2_lr = lr.score(X_test,Y_test)
+print("Linear Regression R-Squared =", r2_lr)
+
+lm_fit = smf.ols('targetvariable ~ FV1 + FV2 + FV3 + FV4',df).fit()
+print(lm_fit.summary())
+print("R-Squared =", lm_fit.rsquared)
+print("Adjusted R-Squared =",lm_fit.rsquared_adj)
+
+ridge = Ridge(alpha=10)
+ridge.fit(X_train,Y_train)
+print("Ridge Coefficients =")
+
+print(pd.Series(ridge.coef_,index=X.columns))
+pred_ridge = ridge.predict(X_test)
+mse_ridge = mean_squared_error(Y_test,pred_ridge)
+print("Ridge Test MSE =", mse_ridge)
+r2_ridge = ridge.score(X_test,Y_test)
+print("Ridge R-Squared =", r2_ridge)
+alphas = 10 ** np.linspace(10,-2,100) * 0.5
+ridgecv = RidgeCV(alphas=alphas)
+ridgecv.fit(X_scaled,Y)
+print("Best Ridge Alpha =",ridgecv.alpha_)
+
+lasso = Lasso(alpha=10)
+lasso.fit(X_train,Y_train)
+print("Lasso Coefficients =")
+print(pd.Series(lasso.coef_,index=X.columns))
+print("Notice: Lasso may set coefficients to EXACTLY 0")
+pred_lasso = lasso.predict(X_test)
+mse_lasso = mean_squared_error(Y_test,pred_lasso)
+print("Lasso Test MSE =", mse_lasso)
+r2_lasso = lasso.score(X_test,Y_test)
+print("Lasso R-Squared =", r2_lasso)
+model = LinearRegression()
+
+kfold = KFold(10,random_state=0,shuffle=True)
+r2_cv = cross_val_score(model,X_scaled,Y,cv=kfold,scoring='r2')
+print("R2 Score Per Fold =")
+print(r2_cv)
+print("Average Accuracy (R2 Score) =",np.mean(r2_cv))""")
+
+    def logi(self):
+        """Logistic regression with VIF, confusion matrix, classification report, K-Fold."""
+        print("""\
+import numpy as np
+import pandas as pd
+from sklearn.linear_model import LogisticRegression
+from sklearn.model_selection import (train_test_split,KFold,cross_val_score)
+from sklearn.metrics import (confusion_matrix,accuracy_score,classification_report)
+from statsmodels.stats.outliers_influence import (variance_inflation_factor)
+import statsmodels.api as sm
+
+df = pd.read_csv('data.csv')
+
+print(df.head())
+print(df.info())
+
+X = df[['FV1','FV2','FV3','FV4']]
+Y = df['targetvariable']
+
+X_vif = sm.add_constant(X)
+vif_data = pd.DataFrame()
+vif_data["Feature"] = X_vif.columns
+vif_data["VIF"] = [variance_inflation_factor(X_vif.values,i)
+    for i in range(X_vif.shape[1])]
+print(vif_data)
+X_train, X_test, Y_train, Y_test = train_test_split(X,Y,test_size=0.20,random_state=123)
+print("Train Shape =", X_train.shape)
+print("Test Shape =", X_test.shape)
+logit = LogisticRegression()
+logit.fit(X_train, Y_train)
+print("Intercept =", logit.intercept_)
+print("Coefficients =", logit.coef_)
+Y_pred = logit.predict(X_test)
+print("Predictions =")
+print(Y_pred)
+
+cm = confusion_matrix(Y_test,Y_pred)
+print("Confusion Matrix =")
+print(cm)
+
+accuracy = accuracy_score(Y_test,Y_pred)
+print("Accuracy =", accuracy)
+print(classification_report(Y_test,Y_pred))
+K = 5
+kfold = KFold(K,random_state=0,shuffle=True)
+
+accuracy_cv = cross_val_score(logit,X,Y,cv=kfold,scoring='accuracy')
+print("Accuracy Per Fold =")
+print(accuracy_cv)
+print("Average Accuracy =",np.mean(accuracy_cv))""")
+
+    def annova(self):
+        """ANOVA — One-way, Two-way, and Tukey post-hoc."""
+        print("""\
+import pandas as pd
+import statsmodels.api as sm
+from statsmodels.formula.api import ols
+from statsmodels.stats.multicomp import pairwise_tukeyhsd
+
+
+## ============================================================
+## 1. ONE-WAY ANOVA
+## ============================================================
+
+df = pd.read_csv('data.csv')
+
+df['column_name'] = df['column_name'].astype('category')
+
+df.head()
+df.info()
+
+oneway_fit = ols('target ~ factor', data=df).fit()
+oneway_anova = sm.stats.anova_lm(oneway_fit, typ=1)
+print(oneway_anova)
+
+# IF 2 Factor variables are given they are to be compared individually
+
+# If the P value of anova is less than 0.05 then Use Tukey for the Factor Variable.
+
+
+## ============================================================
+## 2. TWO-WAY ANOVA
+## ============================================================
+
+df2 = pd.read_csv('cars.csv')
+
+twoway_fit = ols('target ~ C(factor1)+C(factor2)+C(factor1):C(factor2)', data=df2).fit()
+twoway_anova = sm.stats.anova_lm(twoway_fit, typ=2)
+
+
+## ============================================================
+## 3. TUKEY POST-HOC TEST
+## ============================================================
+
+tukey = pairwise_tukeyhsd(df1["target"],groups=df1["factor"])
+tukey._results_table""")
+
+    def manova(self):
+        """MANOVA — One-way and Two-way."""
+        print("""\
+import pandas as pd
+from statsmodels.multivariate.manova import MANOVA
+
+
+## ============================================================
+## 1. ONE-WAY MANOVA
+## ============================================================
+
+url = 'https://vincentarelbundock.github.io/Rdatasets/csv/datasets/iris.csv'
+df = pd.read_csv(url)
+print(df.head())
+df.columns = df.columns.str.replace(".", "_")
+print(df.head())
+
+maov = MANOVA.from_formula('target1 + target2 + target3 + ...  ~ factor', data=df)
+print(maov.mv_test())
+
+
+## ============================================================
+## 2. TWO-WAY MANOVA
+## ============================================================
+
+maov = MANOVA.from_formula('target1 + target2 + target3 + ...  ~ factor1 + factor2', data=df)
+print(maov.mv_test())
+
+
+# If p value > 0.05, we reject H0""")
+
+
+get = _Get()

scypyy-0.7.0/scypyy.egg-info/PKG-INFO

@@ -0,0 +1,32 @@
+Metadata-Version: 2.4
+Name: scypyy
+Version: 0.7.0
+Summary: A curated collection.
+License-Expression: MIT
+Project-URL: Homepage, https://google.com
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Dynamic: requires-python
+
+# scypyy
+
+A curated collection.
+## Installation
+
+```bash
+pip install scypyy
+```
+
+## Usage
+
+```python
+import scypyy
+
+print(scypyy.get())
+```
+
+This prints a help.

scypyy-0.7.0/scypyy.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+README.md
+pyproject.toml
+setup.py
+scypyy/__init__.py
+scypyy/core.py
+scypyy.egg-info/PKG-INFO
+scypyy.egg-info/SOURCES.txt
+scypyy.egg-info/dependency_links.txt
+scypyy.egg-info/top_level.txt

scypyy-0.7.0/scypyy.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

scypyy-0.7.0/scypyy.egg-info/top_level.txt

@@ -0,0 +1 @@
+scypyy

scypyy-0.7.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

scypyy-0.7.0/setup.py

@@ -0,0 +1,17 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="scypyy",
+    version="0.7.0",
+    packages=find_packages(),
+    description="A curated collection.",
+    long_description=open("README.md").read(),
+    long_description_content_type="text/markdown",
+    python_requires=">=3.8",
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "Operating System :: OS Independent",
+        "Intended Audience :: Science/Research",
+        "Topic :: Scientific/Engineering",
+    ],
+)