2983 lines
516 KiB
Plaintext
2983 lines
516 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a80529e4",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Analisi dei dati con il sonar\n",
|
||
"Minimo Indice:\n",
|
||
"- Analisi dei dati statici\n",
|
||
"- Analisi dei dati dinamici\n",
|
||
" - Sonar\n",
|
||
" - Cronometro"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "32702b8f",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Import delle librerie e set di variabili gloabali"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "f34c5b88",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"import pandas as pd\n",
|
||
"import scipy as sc\n",
|
||
"from scipy.stats import chi2\n",
|
||
"import seaborn as sns\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import matplotlib as mpl\n",
|
||
"import statsmodels.api as sm\n",
|
||
"\n",
|
||
"\n",
|
||
"g = 9.807\n",
|
||
"ug = 0.001\n",
|
||
"\n",
|
||
"m_mol = 15.43\n",
|
||
"um_mol = 0.01"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "fd0b8b1d",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Lettura dei dati e calcolo delle deviazioni standard campionarie\n",
|
||
"- Lettura del CSV\n",
|
||
"- Creazione del data frame\n",
|
||
"- Deviazioni standard\n",
|
||
"\n",
|
||
"ATTENZIONE: Linea cursed ~17"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "08efb2be",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"df = pd.read_csv(r'dinamica1.csv')\n",
|
||
"\n",
|
||
"def calcola_stats(df, prefix, err_arbitrario):\n",
|
||
" cols = [col for col in df.columns if col.startswith(prefix)]\n",
|
||
"\n",
|
||
" def riga_stats(row):\n",
|
||
" valori = row[cols].dropna()\n",
|
||
" n = len(valori)\n",
|
||
"\n",
|
||
" if n == 0:\n",
|
||
" return pd.Series({prefix: np.nan, f\"u{prefix}\": np.nan})\n",
|
||
" elif n == 1:\n",
|
||
" return pd.Series({prefix: valori.iloc[0], f\"u{prefix}\": err_arbitrario})\n",
|
||
" else:\n",
|
||
" media = valori.mean()\n",
|
||
" sigma = valori.std(ddof=1)\n",
|
||
" return pd.Series({prefix: media, f\"u{prefix}\": sigma})\n",
|
||
"\n",
|
||
" stats = df.apply(riga_stats, axis=1)\n",
|
||
" df[prefix] = stats[prefix]\n",
|
||
" df[f\"u{prefix}\"] = stats[f\"u{prefix}\"]\n",
|
||
"\n",
|
||
" return df\n",
|
||
"\n",
|
||
"\n",
|
||
"df = calcola_stats(df, \"w\", err_arbitrario=0.0002)\n",
|
||
"df = calcola_stats(df, \"m\", err_arbitrario=0.0028867513)\n",
|
||
"df = calcola_stats(df, \"c\", err_arbitrario=0.01)\n",
|
||
"df = calcola_stats(df, \"a\", err_arbitrario=0.01)\n",
|
||
"df = calcola_stats(df, \"t\", err_arbitrario=0.01)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "5494409f",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>m1</th>\n",
|
||
" <th>a1</th>\n",
|
||
" <th>ua1</th>\n",
|
||
" <th>w1</th>\n",
|
||
" <th>uw1</th>\n",
|
||
" <th>c1</th>\n",
|
||
" <th>uc1</th>\n",
|
||
" <th>a2</th>\n",
|
||
" <th>ua2</th>\n",
|
||
" <th>w2</th>\n",
|
||
" <th>uw2</th>\n",
|
||
" <th>c2</th>\n",
|
||
" <th>uc2</th>\n",
|
||
" <th>w</th>\n",
|
||
" <th>uw</th>\n",
|
||
" <th>m</th>\n",
|
||
" <th>um</th>\n",
|
||
" <th>c</th>\n",
|
||
" <th>uc</th>\n",
|
||
" <th>a</th>\n",
|
||
" <th>ua</th>\n",
|
||
" <th>t</th>\n",
|
||
" <th>ut</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>108.610000</td>\n",
|
||
" <td>9.210</td>\n",
|
||
" <td>0.029</td>\n",
|
||
" <td>14.2459</td>\n",
|
||
" <td>0.0008</td>\n",
|
||
" <td>268.151</td>\n",
|
||
" <td>0.020</td>\n",
|
||
" <td>10.690</td>\n",
|
||
" <td>0.040</td>\n",
|
||
" <td>14.2434</td>\n",
|
||
" <td>0.0009</td>\n",
|
||
" <td>268.326</td>\n",
|
||
" <td>0.026</td>\n",
|
||
" <td>14.24465</td>\n",
|
||
" <td>0.001768</td>\n",
|
||
" <td>108.610000</td>\n",
|
||
" <td>0.002887</td>\n",
|
||
" <td>268.2385</td>\n",
|
||
" <td>0.123744</td>\n",
|
||
" <td>9.9500</td>\n",
|
||
" <td>1.046518</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>128.636667</td>\n",
|
||
" <td>10.037</td>\n",
|
||
" <td>0.025</td>\n",
|
||
" <td>13.1939</td>\n",
|
||
" <td>0.0007</td>\n",
|
||
" <td>259.605</td>\n",
|
||
" <td>0.018</td>\n",
|
||
" <td>9.744</td>\n",
|
||
" <td>0.027</td>\n",
|
||
" <td>13.1913</td>\n",
|
||
" <td>0.0009</td>\n",
|
||
" <td>259.745</td>\n",
|
||
" <td>0.020</td>\n",
|
||
" <td>13.19260</td>\n",
|
||
" <td>0.001838</td>\n",
|
||
" <td>128.636667</td>\n",
|
||
" <td>0.002887</td>\n",
|
||
" <td>259.6750</td>\n",
|
||
" <td>0.098995</td>\n",
|
||
" <td>9.8905</td>\n",
|
||
" <td>0.207182</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>148.380000</td>\n",
|
||
" <td>9.930</td>\n",
|
||
" <td>0.030</td>\n",
|
||
" <td>12.3469</td>\n",
|
||
" <td>0.0007</td>\n",
|
||
" <td>251.525</td>\n",
|
||
" <td>0.021</td>\n",
|
||
" <td>11.410</td>\n",
|
||
" <td>0.030</td>\n",
|
||
" <td>12.3461</td>\n",
|
||
" <td>0.0006</td>\n",
|
||
" <td>251.542</td>\n",
|
||
" <td>0.023</td>\n",
|
||
" <td>12.34650</td>\n",
|
||
" <td>0.000566</td>\n",
|
||
" <td>148.380000</td>\n",
|
||
" <td>0.002887</td>\n",
|
||
" <td>251.5335</td>\n",
|
||
" <td>0.012021</td>\n",
|
||
" <td>10.6700</td>\n",
|
||
" <td>1.046518</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>168.530000</td>\n",
|
||
" <td>11.340</td>\n",
|
||
" <td>0.030</td>\n",
|
||
" <td>11.6345</td>\n",
|
||
" <td>0.0005</td>\n",
|
||
" <td>243.211</td>\n",
|
||
" <td>0.021</td>\n",
|
||
" <td>11.500</td>\n",
|
||
" <td>0.030</td>\n",
|
||
" <td>11.6344</td>\n",
|
||
" <td>0.0006</td>\n",
|
||
" <td>243.130</td>\n",
|
||
" <td>0.021</td>\n",
|
||
" <td>11.63445</td>\n",
|
||
" <td>0.000071</td>\n",
|
||
" <td>168.530000</td>\n",
|
||
" <td>0.002887</td>\n",
|
||
" <td>243.1705</td>\n",
|
||
" <td>0.057276</td>\n",
|
||
" <td>11.4200</td>\n",
|
||
" <td>0.113137</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" m1 a1 ua1 w1 uw1 c1 uc1 a2 ua2 \\\n",
|
||
"0 108.610000 9.210 0.029 14.2459 0.0008 268.151 0.020 10.690 0.040 \n",
|
||
"1 128.636667 10.037 0.025 13.1939 0.0007 259.605 0.018 9.744 0.027 \n",
|
||
"2 148.380000 9.930 0.030 12.3469 0.0007 251.525 0.021 11.410 0.030 \n",
|
||
"3 168.530000 11.340 0.030 11.6345 0.0005 243.211 0.021 11.500 0.030 \n",
|
||
"\n",
|
||
" w2 uw2 c2 uc2 w uw m um \\\n",
|
||
"0 14.2434 0.0009 268.326 0.026 14.24465 0.001768 108.610000 0.002887 \n",
|
||
"1 13.1913 0.0009 259.745 0.020 13.19260 0.001838 128.636667 0.002887 \n",
|
||
"2 12.3461 0.0006 251.542 0.023 12.34650 0.000566 148.380000 0.002887 \n",
|
||
"3 11.6344 0.0006 243.130 0.021 11.63445 0.000071 168.530000 0.002887 \n",
|
||
"\n",
|
||
" c uc a ua t ut \n",
|
||
"0 268.2385 0.123744 9.9500 1.046518 NaN NaN \n",
|
||
"1 259.6750 0.098995 9.8905 0.207182 NaN NaN \n",
|
||
"2 251.5335 0.012021 10.6700 1.046518 NaN NaN \n",
|
||
"3 243.1705 0.057276 11.4200 0.113137 NaN NaN "
|
||
]
|
||
},
|
||
"execution_count": 4,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"pd.set_option('display.max_columns', None)\n",
|
||
"pd.set_option('display.width', None)\n",
|
||
"\n",
|
||
"df"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "9b8d8cb4",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Analisi statica"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "fd1b1164",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Permutazioni"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "976d5531",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[(0, 1), (0, 2), (0, 3), (1, 2), (1, 3), (2, 3)]\n",
|
||
"6\n",
|
||
"############################################################\n",
|
||
"[ 8.5635 16.705 25.068 8.1415 16.5045 8.363 ]\n",
|
||
"[0.15846924 0.12432618 0.13635615 0.09972211 0.11437001 0.0585235 ]\n",
|
||
"############################################################\n",
|
||
"[-20.02666667 -39.77 -59.92 -19.74333333 -39.89333333\n",
|
||
" -20.15 ]\n",
|
||
"[0.00408248 0.00408248 0.00408248 0.00408248 0.00408248 0.00408248]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"perm = [(x,i) for x in range(0,len(df)) for i in range(x+1,len(df))]\n",
|
||
"\n",
|
||
"este = np.array([df.c[x] - df.c[j] for x,j in perm])\n",
|
||
"ueste = np.array([np.sqrt(df.uc[x]**2 + df.uc[j]**2) for x,j in perm])\n",
|
||
"\n",
|
||
"masse = np.array([df.m[x] - df.m[j] for x,j in perm])\n",
|
||
"umasse = np.array([np.sqrt(df.um[x]**2 + df.um[j]**2) for x,j in perm])\n",
|
||
"\n",
|
||
"\n",
|
||
"print(perm)\n",
|
||
"print(len(perm))\n",
|
||
"\n",
|
||
"print(\"#\"* 60)\n",
|
||
"print(este)\n",
|
||
"print(ueste)\n",
|
||
"\n",
|
||
"print(\"#\"* 60)\n",
|
||
"print(masse)\n",
|
||
"print(umasse)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "d37fbd7c",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Calcolo dei K e media pesata\n",
|
||
"- Calcolo del K\n",
|
||
"- Calcolo della media pesata (sui K)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "2ad19283",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[22.93472529 23.34776354 23.44165629 23.78221089 23.70468175 23.62920603]\n",
|
||
"[0.42444376 0.17379748 0.12754214 0.29135079 0.16430027 0.16544183]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"F = masse * g\n",
|
||
"uF = np.sqrt((g * umasse)**2 + (masse * ug)**2)\n",
|
||
"\n",
|
||
"K = - F / este\n",
|
||
"uK = np.sqrt((1/este)**2 * uF**2 + (F / este**2)**2 * ueste**2 )\n",
|
||
"\n",
|
||
"\n",
|
||
"print(K)\n",
|
||
"print(uK)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "5f59d6c9",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"K-medio: 23.52082621035826\n",
|
||
"sigmaC: 0.07342397251895814\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"def mediaPesata(x, ux, dim = 0):\n",
|
||
" x_arr = x.to_numpy() if isinstance(x, (pd.Series, pd.DataFrame)) else np.asarray(x)\n",
|
||
" sigma_arr = ux.to_numpy() if isinstance(ux, (pd.Series, pd.DataFrame)) else np.asarray(ux)\n",
|
||
"\n",
|
||
" w = 1.0 / (sigma_arr ** 2)\n",
|
||
"\n",
|
||
" num = np.nansum(w * x_arr, axis=dim)\n",
|
||
" den = np.nansum(w, axis=dim)\n",
|
||
"\n",
|
||
" media = num / den\n",
|
||
" sigma = np.sqrt(1.0 / den)\n",
|
||
"\n",
|
||
" return media, sigma\n",
|
||
"\n",
|
||
"media, uA = mediaPesata(K, uK)\n",
|
||
"print(\"K-medio:\", media)\n",
|
||
"print(\"sigmaC: \", uA)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "21baebb4",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Analisi con regressioni e grafici\n",
|
||
"Ogni blocco ha:\n",
|
||
"- Regressione\n",
|
||
"- grafico\n",
|
||
"- chi^2\n",
|
||
"\n",
|
||
"Nota: Ax + B"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "5be377eb",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"sns.set_theme(style=\"whitegrid\")\n",
|
||
"\n",
|
||
"data = pd.DataFrame({\n",
|
||
" \"x\": este,\n",
|
||
" \"ux\": ueste,\n",
|
||
" \"y\": - F,\n",
|
||
" \"uy\": uF\n",
|
||
"})"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "6ec60a92",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Regressione lineare \"OLS\"\n",
|
||
"\n",
|
||
"Non tiene conto dei nostri errori, un risultato puro e semplice"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"id": "aefe7756",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" OLS Regression Results \n",
|
||
"==============================================================================\n",
|
||
"Dep. Variable: y R-squared: 1.000\n",
|
||
"Model: OLS Adj. R-squared: 1.000\n",
|
||
"Method: Least Squares F-statistic: 1.044e+04\n",
|
||
"Date: Sun, 05 Apr 2026 Prob (F-statistic): 5.50e-08\n",
|
||
"Time: 21:57:04 Log-Likelihood: -14.807\n",
|
||
"No. Observations: 6 AIC: 33.61\n",
|
||
"Df Residuals: 4 BIC: 33.20\n",
|
||
"Df Model: 1 \n",
|
||
"Covariance Type: nonrobust \n",
|
||
"==============================================================================\n",
|
||
" coef std err t P>|t| [0.025 0.975]\n",
|
||
"------------------------------------------------------------------------------\n",
|
||
"const 0.1355 3.495 0.039 0.971 -9.569 9.840\n",
|
||
"x 23.4652 0.230 102.161 0.000 22.827 24.103\n",
|
||
"==============================================================================\n",
|
||
"Omnibus: nan Durbin-Watson: 0.555\n",
|
||
"Prob(Omnibus): nan Jarque-Bera (JB): 0.395\n",
|
||
"Skew: -0.285 Prob(JB): 0.821\n",
|
||
"Kurtosis: 1.880 Cond. No. 37.4\n",
|
||
"==============================================================================\n",
|
||
"\n",
|
||
"Notes:\n",
|
||
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE:\n",
|
||
"Aols = 23.46517 ± 0.22969\n",
|
||
"Bols = 0.13548 ± 3.49525\n",
|
||
"R² = 0.99962\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/home/jack/uni/lab/.venv/lib/python3.13/site-packages/statsmodels/stats/stattools.py:74: ValueWarning: omni_normtest is not valid with less than 8 observations; 6 samples were given.\n",
|
||
" warn(\"omni_normtest is not valid with less than 8 observations; %i \"\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"X = sm.add_constant(data[\"x\"])\n",
|
||
"model = sm.OLS(data[\"y\"], X).fit()\n",
|
||
"\n",
|
||
"print(model.summary())\n",
|
||
"\n",
|
||
"# Estrazione parametri\n",
|
||
"Bols = model.params[\"const\"]\n",
|
||
"Aols = model.params[\"x\"]\n",
|
||
"uBols = model.bse[\"const\"]\n",
|
||
"uAols = model.bse[\"x\"]\n",
|
||
"R2 = model.rsquared\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE:\")\n",
|
||
"print(f\"Aols = {Aols:.5f} ± {uAols:.5f}\")\n",
|
||
"print(f\"Bols = {Bols:.5f} ± {uBols:.5f}\")\n",
|
||
"print(f\"R² = {R2:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "8d795186",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.figure(figsize=(10,6))\n",
|
||
"\n",
|
||
"# Seaborn scatter\n",
|
||
"sns.scatterplot( data=data,\n",
|
||
" x=\"x\",\n",
|
||
" y=\"y\",\n",
|
||
" s=7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Barre d’errore\n",
|
||
"plt.errorbar(\n",
|
||
" data[\"x\"],\n",
|
||
" data[\"y\"],\n",
|
||
" xerr=data[\"ux\"],\n",
|
||
" yerr=data[\"uy\"],\n",
|
||
" fmt=\"none\",\n",
|
||
" ecolor=\"gray\",\n",
|
||
" elinewidth=1,\n",
|
||
" capsize=3,\n",
|
||
" alpha=0.7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Linea di regressione\n",
|
||
"xfit = np.linspace(0, data[\"x\"].max(), 200)\n",
|
||
"yfit = Bols + Aols * xfit\n",
|
||
"\n",
|
||
"plt.plot(\n",
|
||
" xfit,\n",
|
||
" yfit,\n",
|
||
" color=\"crimson\",\n",
|
||
" linewidth=1,\n",
|
||
" zorder=10,\n",
|
||
" label=\"Fit lineare OLS\"\n",
|
||
")\n",
|
||
"\n",
|
||
"plt.xlim(left=0)\n",
|
||
"plt.ylim(bottom=0)\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.xlabel(\"Δx (mm)\")\n",
|
||
"plt.ylabel(\"Forza F (mN)\")\n",
|
||
"plt.title(\"Legge di Hooke — punti permutati con errorbar\")\n",
|
||
"plt.legend()\n",
|
||
"plt.grid(True, linestyle=\"--\", alpha=0.1)\n",
|
||
"\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 11,
|
||
"id": "1d42b009",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Chi² = 6.07430\n",
|
||
"GdL = 4\n",
|
||
"Chi² rid = 1.51858\n",
|
||
"P(0, chi²)= 0.80633\n",
|
||
"\n",
|
||
"\n",
|
||
"############################################################\n",
|
||
"capiamo quale dato sta contribuendo maggiormente\n",
|
||
"0 1.582374\n",
|
||
"1 0.516368\n",
|
||
"2 0.051305\n",
|
||
"3 1.091998\n",
|
||
"4 2.022571\n",
|
||
"5 0.809686\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"F_fit = Bols + Aols * data[\"x\"]\n",
|
||
"sigma = np.sqrt(data[\"uy\"]**2 + (Aols * data[\"ux\"])**2)\n",
|
||
"\n",
|
||
"chi2_val = np.sum( ((data[\"y\"] - F_fit) / sigma)**2 )\n",
|
||
"\n",
|
||
"N = len(data)\n",
|
||
"nu = N - 2\n",
|
||
"\n",
|
||
"chi2_red = chi2_val / nu\n",
|
||
"Pols = chi2.cdf(chi2_val, df=nu)\n",
|
||
"\n",
|
||
"\n",
|
||
"print(f\"Chi² = {chi2_val:.5f}\")\n",
|
||
"print(f\"GdL = {nu}\")\n",
|
||
"print(f\"Chi² rid = {chi2_red:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {Pols:.5f}\")\n",
|
||
"print(\"\\n\\n\" + \"#\"*60)\n",
|
||
"print(\"capiamo quale dato sta contribuendo maggiormente\")\n",
|
||
"print(((data[\"y\"] - F_fit) / sigma)**2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "9f26f65e",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Regressione lineare Carpi"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"id": "6a910226",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Ax + B : \n",
|
||
"AC = 23.3952 +- 0.1756\n",
|
||
"BC = 1.8060 +- 2.2463\n",
|
||
"cov_ABC = -0.358328\n",
|
||
"P(0, chi²)= 0.7197\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"def sigma_y_equiv(x, y, sigma_x, sigma_y):\n",
|
||
" # Stima iniziale di A con sola sigma_y\n",
|
||
" sy2 = sigma_y**2\n",
|
||
" Sw = np.sum(1 / sy2)\n",
|
||
" Sx = np.sum(x / sy2)\n",
|
||
" Sxx = np.sum(x**2 / sy2)\n",
|
||
" Sy = np.sum(y / sy2)\n",
|
||
" Sxy = np.sum(x * y / sy2)\n",
|
||
" delta = Sxx * Sw - Sx**2\n",
|
||
" A_est = (Sxy * Sw - Sx * Sy) / delta\n",
|
||
"\n",
|
||
" # Propagazione\n",
|
||
" sigma_eq = np.sqrt(sigma_y**2 + A_est**2 * sigma_x**2)\n",
|
||
" return sigma_eq\n",
|
||
"\n",
|
||
"\n",
|
||
"def reg_lin(x, y, sigma_x, sigma_y):\n",
|
||
" x = np.asarray(x, dtype=float)\n",
|
||
" y = np.asarray(y, dtype=float)\n",
|
||
" sigma_x = np.asarray(sigma_x, dtype=float)\n",
|
||
" sigma_y = np.asarray(sigma_y, dtype=float)\n",
|
||
"\n",
|
||
" # Propagazione errore x → y\n",
|
||
" sigma_y_eq = sigma_y_equiv(x, y, sigma_x, sigma_y)\n",
|
||
"\n",
|
||
" # Somme pesate\n",
|
||
" w = 1.0 / sigma_y_eq**2\n",
|
||
" Sw = np.sum(w)\n",
|
||
" Sx = np.sum(w * x)\n",
|
||
" Sxx = np.sum(w * x**2)\n",
|
||
" Sy = np.sum(w * y)\n",
|
||
" Sxy = np.sum(w * x * y)\n",
|
||
" delta = Sxx * Sw - Sx**2\n",
|
||
"\n",
|
||
" # Parametri\n",
|
||
" A = (Sxy * Sw - Sx * Sy) / delta\n",
|
||
" B = (Sxx * Sy - Sxy * Sx) / delta\n",
|
||
" sigma_A = np.sqrt(Sw / delta)\n",
|
||
" sigma_B = np.sqrt(Sxx / delta)\n",
|
||
" cov_AB = -Sx / delta\n",
|
||
"\n",
|
||
" # Chi quadro\n",
|
||
" x2 = np.sum((y - A * x - B)**2 / sigma_y_eq**2)\n",
|
||
" dof = len(x) - 2\n",
|
||
" chi = sc.stats.chi2.cdf(x2, dof) # P(X² > x2)\n",
|
||
"\n",
|
||
" return A, B, sigma_A, sigma_B, cov_AB, chi\n",
|
||
"\n",
|
||
"\n",
|
||
"AC, BC, uAC, uBC, covABC, chiC = reg_lin(data[\"x\"], data[\"y\"], data[\"ux\"], data[\"uy\"])\n",
|
||
"print(\"Ax + B : \")\n",
|
||
"print(f\"AC = {AC:.4f} +- {uAC:.4f}\")\n",
|
||
"print(f\"BC = {BC:.4f} +- {uBC:.4f}\")\n",
|
||
"print(f\"cov_ABC = {covABC:.6f}\")\n",
|
||
"print(f\"P(0, chi²)= {chiC:.4f}\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 13,
|
||
"id": "b49ec5a3",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.figure(figsize=(10,6))\n",
|
||
"\n",
|
||
"# Seaborn scatter\n",
|
||
"sns.scatterplot(\n",
|
||
" data=data,\n",
|
||
" x=\"x\",\n",
|
||
" y=\"y\",\n",
|
||
" s=7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Barre d’errore\n",
|
||
"plt.errorbar(\n",
|
||
" data[\"x\"],\n",
|
||
" data[\"y\"],\n",
|
||
" xerr=data[\"ux\"],\n",
|
||
" yerr=data[\"uy\"],\n",
|
||
" fmt=\"none\",\n",
|
||
" ecolor=\"gray\",\n",
|
||
" elinewidth=1,\n",
|
||
" capsize=3,\n",
|
||
" alpha=0.7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Linea di regressione\n",
|
||
"xfit = np.linspace(0, data[\"x\"].max(), 200)\n",
|
||
"yfit = BC + AC * xfit\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.plot(\n",
|
||
" xfit,\n",
|
||
" yfit,\n",
|
||
" color=\"crimson\",\n",
|
||
" linewidth=1,\n",
|
||
" zorder=10,\n",
|
||
" label=\"Fit lineare Carpi\"\n",
|
||
")\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.xlim(left=0)\n",
|
||
"plt.ylim(bottom=0)\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.xlabel(\"Δx (mm)\")\n",
|
||
"plt.ylabel(\"Forza F (mN)\")\n",
|
||
"plt.title(\"Legge di Hooke — punti permutati con errorbar\")\n",
|
||
"plt.legend()\n",
|
||
"plt.grid(True, linestyle=\"--\", alpha=0.1)\n",
|
||
"\n",
|
||
"plt.show()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 14,
|
||
"id": "538ddb98",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Chi² = 5.10905\n",
|
||
"GdL = 4\n",
|
||
"Chi² rid = 1.27726\n",
|
||
"P(0, chi²)= 0.72371\n",
|
||
"\n",
|
||
"\n",
|
||
"############################################################\n",
|
||
"capiamo quale dato sta contribuendo maggiormente\n",
|
||
"0 2.404581\n",
|
||
"1 0.797907\n",
|
||
"2 0.040448\n",
|
||
"3 0.332099\n",
|
||
"4 1.521888\n",
|
||
"5 0.012127\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"F_fit = BC + AC * data[\"x\"]\n",
|
||
"sigma = np.sqrt(data[\"uy\"]**2 + (AC * data[\"ux\"])**2)\n",
|
||
"\n",
|
||
"\n",
|
||
"chi2_val = np.sum( ((data[\"y\"] - F_fit) / sigma)**2 )\n",
|
||
"\n",
|
||
"N = len(data)\n",
|
||
"nu = N - 2\n",
|
||
"\n",
|
||
"chi2_red = chi2_val / nu\n",
|
||
"PC = chi2.cdf(chi2_val, df=nu)\n",
|
||
"\n",
|
||
"\n",
|
||
"print(f\"Chi² = {chi2_val:.5f}\")\n",
|
||
"print(f\"GdL = {nu}\")\n",
|
||
"print(f\"Chi² rid = {chi2_red:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {PC:.5f}\")\n",
|
||
"print(\"\\n\\n\" + \"#\"*60)\n",
|
||
"print(\"capiamo quale dato sta contribuendo maggiormente\")\n",
|
||
"print(((data[\"y\"] - F_fit) / sigma)**2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "4ec42f61",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Regressione lineare pesata Yorkfit "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 15,
|
||
"id": "c7f54cf3",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"AY = 23.4018867 ± 0.1749174\n",
|
||
"BY = 1.7284277 ± 2.2381063\n",
|
||
"cov_ABY = -0.35570868522503013\n",
|
||
"chi² = 5.10759\n",
|
||
"chi² rid = 1.27690\n",
|
||
"P(0, chi²)= 0.72357\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"def york_fit(x, y, sx, sy, max_iter=50, tol=1e-15):\n",
|
||
" # Pesi iniziali\n",
|
||
" wx = 1 / sx**2\n",
|
||
" wy = 1 / sy**2\n",
|
||
"\n",
|
||
" # Stima iniziale della pendenza (OLS y|x)\n",
|
||
" A = np.cov(x, y, aweights=wy)[0,1] / np.cov(x, x, aweights=wy)[0,1]\n",
|
||
"\n",
|
||
" for _ in range(max_iter):\n",
|
||
" A_old = A\n",
|
||
"\n",
|
||
" # 1) Pesi combinati\n",
|
||
" Wi = (wx * wy) / (A**2 * wy + wx)\n",
|
||
"\n",
|
||
" # 2) x e y pesati (eq. 10)\n",
|
||
" X_bar = np.sum(Wi * x) / np.sum(Wi)\n",
|
||
" Y_bar = np.sum(Wi * y) / np.sum(Wi)\n",
|
||
"\n",
|
||
" # 3) Variabili centrate\n",
|
||
" Ui = x - X_bar\n",
|
||
" Vi = y - Y_bar\n",
|
||
"\n",
|
||
" # 4) beta\n",
|
||
" beta_i = Wi * (Ui / wy + A * Vi / wx)\n",
|
||
"\n",
|
||
" # 5) Aggiornamento pendenza\n",
|
||
" A = np.sum(Wi * beta_i * Vi) / np.sum(Wi * beta_i * Ui)\n",
|
||
"\n",
|
||
" # Convergenza\n",
|
||
" if abs(A - A_old) < tol:\n",
|
||
" break\n",
|
||
"\n",
|
||
" # 6) Intercetta\n",
|
||
" B = Y_bar - A * X_bar\n",
|
||
"\n",
|
||
" # S = somma Wi (xi - x)**2\n",
|
||
" S = np.sum(Wi * Ui**2)\n",
|
||
"\n",
|
||
" sA = np.sqrt(1 / S)\n",
|
||
" sB = np.sqrt(1 / np.sum(Wi) + X_bar**2 * sA**2)\n",
|
||
"\n",
|
||
" # cov(A,B)\n",
|
||
" cov_AB = -X_bar * sA**2\n",
|
||
"\n",
|
||
" # CHI QUADRATO\n",
|
||
" chi2 = np.sum(Wi * (Vi - A * Ui)**2)\n",
|
||
" dof = len(x) - 2\n",
|
||
" chi2_red = chi2 / dof\n",
|
||
"\n",
|
||
" return A, B, sA, sB, cov_AB, chi2, chi2_red\n",
|
||
"\n",
|
||
"AY, BY, uAY, uBY, cov_ABY, chi2_val, chi2_red = york_fit(data.x, data.y, data.ux, data.uy)\n",
|
||
"PY = chi2.cdf(chi2_val, df=nu)\n",
|
||
"\n",
|
||
"\n",
|
||
"print(f\"AY = {AY:.7f} ± {uAY:.7f}\")\n",
|
||
"print(f\"BY = {BY:.7f} ± {uBY:.7f}\")\n",
|
||
"print(f\"cov_ABY = {cov_ABY}\")\n",
|
||
"print(f\"chi² = {chi2_val:.5f}\")\n",
|
||
"print(f\"chi² rid = {chi2_red:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {PY:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 16,
|
||
"id": "fc824066",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.figure(figsize=(10,6))\n",
|
||
"\n",
|
||
"# Seaborn scatter\n",
|
||
"sns.scatterplot( data=data,\n",
|
||
" x=\"x\",\n",
|
||
" y=\"y\",\n",
|
||
" s=7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Barre d’errore\n",
|
||
"plt.errorbar(\n",
|
||
" data[\"x\"],\n",
|
||
" data[\"y\"],\n",
|
||
" xerr=data[\"ux\"],\n",
|
||
" yerr=data[\"uy\"],\n",
|
||
" fmt=\"none\",\n",
|
||
" ecolor=\"gray\",\n",
|
||
" elinewidth=1,\n",
|
||
" capsize=3,\n",
|
||
" alpha=0.7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Linea di regressione\n",
|
||
"xfit = np.linspace(0, data[\"x\"].max(), 200)\n",
|
||
"yfit = BY + AY * xfit\n",
|
||
"\n",
|
||
"plt.plot(\n",
|
||
" xfit,\n",
|
||
" yfit,\n",
|
||
" color=\"crimson\",\n",
|
||
" linewidth=1,\n",
|
||
" zorder=10,\n",
|
||
" label=\"Fit lineare York\"\n",
|
||
")\n",
|
||
"\n",
|
||
"plt.xlim(left=0)\n",
|
||
"plt.ylim(bottom=0)\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.xlabel(\"Δx (mm)\")\n",
|
||
"plt.ylabel(\"Forza F (mN)\")\n",
|
||
"plt.title(\"Legge di Hooke — punti permutati con errorbar\")\n",
|
||
"plt.legend()\n",
|
||
"plt.grid(True, linestyle=\"--\", alpha=0.1)\n",
|
||
"\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "15a6fec5",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Raccolta finale dei dati caso statico"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 17,
|
||
"id": "1203e1a0",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"RISULTATI senza ERRORE STRUMENTALE INCLUSO:\n",
|
||
"Media pesata K = 23.52083 ± 0.07342\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE OLS:\n",
|
||
"Aols = 23.46517 ± 0.22969\n",
|
||
"Bols = 0.13548 ± 3.49525\n",
|
||
"P(0, chi²)= 0.80633\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE Carpi:\n",
|
||
"Ac = 23.39521 ± 0.17556\n",
|
||
"Bc = 1.80604 ± 2.24633\n",
|
||
"P(0, chi²)= 0.72371\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE York:\n",
|
||
"Ay = 23.40189 ± 0.17492\n",
|
||
"By = 1.72843 ± 2.23811\n",
|
||
"P(0, chi²)= 0.72357\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(\"RISULTATI senza ERRORE STRUMENTALE INCLUSO:\")\n",
|
||
"print(f\"Media pesata K = {media:.5f} ± {uA:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE OLS:\")\n",
|
||
"print(f\"Aols = {Aols:.5f} ± {uAols:.5f}\")\n",
|
||
"print(f\"Bols = {Bols:.5f} ± {uBols:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {Pols:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE Carpi:\")\n",
|
||
"print(f\"Ac = {AC:.5f} ± {uAC:.5f}\")\n",
|
||
"print(f\"Bc = {BC:.5f} ± {uBC:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {PC:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE York:\")\n",
|
||
"print(f\"Ay = {AY:.5f} ± {uAY:.5f}\")\n",
|
||
"print(f\"By = {BY:.5f} ± {uBY:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {PY:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "2dcfef24",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Aggiunta degli errori strumentali"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 18,
|
||
"id": "aaa95426",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"u_strum_m = 0.004082\n",
|
||
"u_strum_Dx = 0.020000\n",
|
||
"uF_strum = 0.072065\n",
|
||
"uK_strum = 0.462991\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"res_b = 0.01\n",
|
||
"res_c = 0.02\n",
|
||
"\n",
|
||
"# Incertezza strumentale su una differenza: res/sqrt(12) * sqrt(2) = res/sqrt(6)\n",
|
||
"u_strum_m = res_b / np.sqrt(6)\n",
|
||
"u_strum_Dx = res_c #incertezza delle misure di C DISCUTERE\n",
|
||
"\n",
|
||
"# Massimo tra campionario e strumentale, punto per punto\n",
|
||
"ueste_strum = np.maximum(ueste, u_strum_Dx)\n",
|
||
"umasse_strum = np.maximum(umasse, u_strum_m)\n",
|
||
"\n",
|
||
"# Worst-case scalare: prendi il massimo anche di ueste_strum\n",
|
||
"uF_strum = np.max(np.sqrt( (g * umasse_strum)**2 + (masse * ug)**2 ))\n",
|
||
"uDx_strum = np.max(ueste_strum)\n",
|
||
"\n",
|
||
"uK_strum = np.max(np.sqrt( (1/este)**2 * uF_strum**2 + (F/este**2)**2 * uDx_strum**2 ))\n",
|
||
"\n",
|
||
"print(f\"u_strum_m = {u_strum_m:.6f}\")\n",
|
||
"print(f\"u_strum_Dx = {u_strum_Dx:.6f}\")\n",
|
||
"print(f\"uF_strum = {uF_strum:.6f}\")\n",
|
||
"print(f\"uK_strum = {uK_strum:.6f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "23be271e",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Propapazione dell'errore strumentale max"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 19,
|
||
"id": "a9f2a9fc",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Media pesata\n",
|
||
"uA_fin = np.sqrt(uA**2 + uK_strum**2)\n",
|
||
"\n",
|
||
"# OLS\n",
|
||
"uAols_fin = np.sqrt(uAols**2 + uK_strum**2)\n",
|
||
"uBols_fin = np.sqrt(uBols**2 + uK_strum**2)\n",
|
||
"\n",
|
||
"# Carpi\n",
|
||
"uAC_fin = np.sqrt(uAC**2 + uK_strum**2)\n",
|
||
"uBC_fin = np.sqrt(uBC**2 + uK_strum**2)\n",
|
||
"\n",
|
||
"# York\n",
|
||
"uAY_fin = np.sqrt(uAY**2 + uK_strum**2)\n",
|
||
"uBY_fin = np.sqrt(uBY**2 + uK_strum**2)\n",
|
||
"\n",
|
||
"\n",
|
||
"# Nuovo uy e ux per ricalcolare i chi^2\n",
|
||
"uy_fin = np.sqrt(data[\"uy\"]**2 + uF_strum**2)\n",
|
||
"ux_fin = np.sqrt(data[\"ux\"]**2 + uDx_strum**2)\n",
|
||
"\n",
|
||
"# OLS\n",
|
||
"F_fit_ols = Bols + Aols * data[\"x\"]\n",
|
||
"sigma_ols = np.sqrt(uy_fin**2 + (Aols * ux_fin)**2)\n",
|
||
"chi2_ols = np.sum(((data[\"y\"] - F_fit_ols) / sigma_ols)**2)\n",
|
||
"GdL = len(data) - 2\n",
|
||
"\n",
|
||
"# Carpi\n",
|
||
"F_fit_c = BC + AC * data[\"x\"]\n",
|
||
"sigma_c = np.sqrt(uy_fin**2 + (AC * ux_fin)**2)\n",
|
||
"chi2_c = np.sum(((data[\"y\"] - F_fit_c) / sigma_c)**2)\n",
|
||
"\n",
|
||
"# York\n",
|
||
"F_fit_y = BY + AY * data[\"x\"]\n",
|
||
"sigma_y_ = np.sqrt(uy_fin**2 + (AY * ux_fin)**2)\n",
|
||
"chi2_y = np.sum(((data[\"y\"] - F_fit_y) / sigma_y_)**2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "41baee7a",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Risultati della propagazione dell'errore strumentale massimo"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 20,
|
||
"id": "c95874fb",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"RISULTATI CON ERRORE STRUMENTALE INCLUSO:\n",
|
||
"Media pesata K = 23.52083 ± 0.46878\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE OLS:\n",
|
||
"Aols = 23.46517 ± 0.51683\n",
|
||
"Bols = 0.13548 ± 3.52578\n",
|
||
"Chi² OLS = 2.10939 | rid = 0.52735 | P = 0.28435\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE Carpi:\n",
|
||
"AC = 23.39521 ± 0.49516\n",
|
||
"BC = 1.80604 ± 2.29355\n",
|
||
"Chi² Carpi = 2.14027 | rid = 0.53507 | P = 0.29002\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE York:\n",
|
||
"AY = 23.40189 ± 0.49493\n",
|
||
"BY = 1.72843 ± 2.28549\n",
|
||
"Chi² York = 2.13715 | rid = 0.53429 | P = 0.28945\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(\"RISULTATI CON ERRORE STRUMENTALE INCLUSO:\")\n",
|
||
"print(f\"Media pesata K = {media:.5f} ± {uA_fin:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE OLS:\")\n",
|
||
"print(f\"Aols = {Aols:.5f} ± {uAols_fin:.5f}\")\n",
|
||
"print(f\"Bols = {Bols:.5f} ± {uBols_fin:.5f}\")\n",
|
||
"print(f\"Chi² OLS = {chi2_ols:.5f} | rid = {chi2_ols/GdL:.5f}\" f\" | P = {chi2.cdf(chi2_ols, df=GdL):.5f}\")\n",
|
||
"\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE Carpi:\")\n",
|
||
"print(f\"AC = {AC:.5f} ± {uAC_fin:.5f}\")\n",
|
||
"print(f\"BC = {BC:.5f} ± {uBC_fin:.5f}\")\n",
|
||
"print(f\"Chi² Carpi = {chi2_c:.5f} | rid = {chi2_c/GdL:.5f}\" f\" | P = {chi2.cdf(chi2_c, df=GdL):.5f}\")\n",
|
||
"\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE York:\")\n",
|
||
"print(f\"AY = {AY:.5f} ± {uAY_fin:.5f}\")\n",
|
||
"print(f\"BY = {BY:.5f} ± {uBY_fin:.5f}\")\n",
|
||
"print(f\"Chi² York = {chi2_y:.5f} | rid = {chi2_y/GdL:.5f}\" f\" | P = {chi2.cdf(chi2_y, df=GdL):.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "fb210b61",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Dinamica Sonar\n",
|
||
"Qui specifico la formula perché non è così ovvia:\n",
|
||
"- $M_{eq} = M + \\frac m 3$\n",
|
||
"- $\\omega = \\frac{2\\pi}{T} \\quad \\Rightarrow \\quad T = \\frac{2\\pi}{\\omega}$\n",
|
||
"- A: coefficiente della regressione lineare $A = \\frac{T^2}{M_{eq}}$\n",
|
||
"- $K = \\frac{4 \\pi^2}{A}$\n",
|
||
"\n",
|
||
"Nota: nelle formule comparirà un $/1000$, questo serve a riportare il valore in unità di misura standard: N/m"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 21,
|
||
"id": "95dde99f",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"0 0.194561\n",
|
||
"1 0.226829\n",
|
||
"2 0.258983\n",
|
||
"3 0.291654\n",
|
||
"Name: w, dtype: float64\n",
|
||
"0 0.000048\n",
|
||
"1 0.000063\n",
|
||
"2 0.000024\n",
|
||
"3 0.000004\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"Meq = df.m + ( m_mol / 3 )\n",
|
||
"uMeq = np.sqrt( df.um**2 + um_mol**2 / 9 )\n",
|
||
"\n",
|
||
"T2 = ( 2 * np.pi / df.w )**2\n",
|
||
"uT2 = np.sqrt( (8*np.pi**2 / df.w**3)**2 * df.uw**2 )\n",
|
||
"\n",
|
||
"print(T2)\n",
|
||
"print(uT2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "7bd743d4",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Calcolo dei K e media pesata\n",
|
||
"- Calcolo della Meq (massa equivalente)\n",
|
||
"- Calcolo della media pesata sui K"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 22,
|
||
"id": "8c9f5b44",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"0 23.081695\n",
|
||
"1 23.283699\n",
|
||
"2 23.402492\n",
|
||
"3 23.508497\n",
|
||
"dtype: float64\n",
|
||
"0 0.005798\n",
|
||
"1 0.006535\n",
|
||
"2 0.002247\n",
|
||
"3 0.000662\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"Ad = T2 / Meq\n",
|
||
"uAd = np.sqrt( (1/Meq)**2 * uT2**2 + (T2/Meq**2)**2 * uMeq**2 )\n",
|
||
"\n",
|
||
"Kd = 4 * np.pi**2 / Ad\n",
|
||
"uKd = np.sqrt( (4 * np.pi**2 / Ad**2)**2 * uAd**2 )\n",
|
||
"\n",
|
||
"Kd /= 1000\n",
|
||
"uKd /= 1000\n",
|
||
"\n",
|
||
"print(Kd)\n",
|
||
"print(uKd)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 23,
|
||
"id": "0d899f17",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"K-medio: 23.49313065421719\n",
|
||
"sigmaC: 0.0006281179024013275\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"def mediaPesata(x, ux, dim = 0):\n",
|
||
" x_arr = x.to_numpy() if isinstance(x, (pd.Series, pd.DataFrame)) else np.asarray(x)\n",
|
||
" sigma_arr = ux.to_numpy() if isinstance(ux, (pd.Series, pd.DataFrame)) else np.asarray(ux)\n",
|
||
"\n",
|
||
" w = 1.0 / (sigma_arr ** 2)\n",
|
||
"\n",
|
||
" num = np.nansum(w * x_arr, axis=dim)\n",
|
||
" den = np.nansum(w, axis=dim)\n",
|
||
"\n",
|
||
" media = num / den\n",
|
||
" sigma = np.sqrt(1.0 / den)\n",
|
||
"\n",
|
||
" return media, sigma\n",
|
||
"\n",
|
||
"KdM, uKdM = mediaPesata(Kd, uKd)\n",
|
||
"print(\"K-medio:\", KdM)\n",
|
||
"print(\"sigmaC: \", uKdM)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "6741544e",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Analisi con regressioni e grafici\n",
|
||
"Ogni blocco ha:\n",
|
||
"- Regressione\n",
|
||
"- grafico\n",
|
||
"- chi^2\n",
|
||
"\n",
|
||
"Nota: Ax + B"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 24,
|
||
"id": "4b4c2682",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"sns.set_theme(style=\"whitegrid\")\n",
|
||
"\n",
|
||
"datad = pd.DataFrame({\n",
|
||
" \"x\": Meq,\n",
|
||
" \"ux\": uMeq,\n",
|
||
" \"y\": T2,\n",
|
||
" \"uy\": uT2\n",
|
||
"})"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "ad203fbd",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Regressione lineare \"OLS\"\n",
|
||
"\n",
|
||
"Non tiene conto dei nostri errori, un risultato puro e semplice"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 25,
|
||
"id": "90d191d5",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" OLS Regression Results \n",
|
||
"==============================================================================\n",
|
||
"Dep. Variable: y R-squared: 1.000\n",
|
||
"Model: OLS Adj. R-squared: 1.000\n",
|
||
"Method: Least Squares F-statistic: 4.713e+05\n",
|
||
"Date: Sun, 05 Apr 2026 Prob (F-statistic): 2.12e-06\n",
|
||
"Time: 21:57:06 Log-Likelihood: 32.343\n",
|
||
"No. Observations: 4 AIC: -60.69\n",
|
||
"Df Residuals: 2 BIC: -61.91\n",
|
||
"Df Model: 1 \n",
|
||
"Covariance Type: nonrobust \n",
|
||
"==============================================================================\n",
|
||
" coef std err t P>|t| [0.025 0.975]\n",
|
||
"------------------------------------------------------------------------------\n",
|
||
"const 0.0101 0.000 29.329 0.001 0.009 0.012\n",
|
||
"x 0.0016 2.36e-06 686.488 0.000 0.002 0.002\n",
|
||
"==============================================================================\n",
|
||
"Omnibus: nan Durbin-Watson: 2.752\n",
|
||
"Prob(Omnibus): nan Jarque-Bera (JB): 0.628\n",
|
||
"Skew: -0.880 Prob(JB): 0.730\n",
|
||
"Kurtosis: 2.180 Cond. No. 948.\n",
|
||
"==============================================================================\n",
|
||
"\n",
|
||
"Notes:\n",
|
||
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE:\n",
|
||
"Adols = 0.00162 ± 0.00000\n",
|
||
"Bdols = 0.01007 ± 0.00034\n",
|
||
"R² = 1.00000\n",
|
||
"Kdols = 24.35158 ± 0.03547\n",
|
||
"KBdols = 3.92000 ± 0.13366\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/home/jack/uni/lab/.venv/lib/python3.13/site-packages/statsmodels/stats/stattools.py:74: ValueWarning: omni_normtest is not valid with less than 8 observations; 4 samples were given.\n",
|
||
" warn(\"omni_normtest is not valid with less than 8 observations; %i \"\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"X = sm.add_constant(datad[\"x\"])\n",
|
||
"model = sm.OLS(datad[\"y\"], X).fit()\n",
|
||
"\n",
|
||
"print(model.summary())\n",
|
||
"\n",
|
||
"# Estrazione parametri\n",
|
||
"Bdols = model.params[\"const\"]\n",
|
||
"Adols = model.params[\"x\"]\n",
|
||
"uBdols = model.bse[\"const\"]\n",
|
||
"uAdols = model.bse[\"x\"]\n",
|
||
"R2 = model.rsquared\n",
|
||
"\n",
|
||
"# Calcolo del K dai parametri\n",
|
||
"Kdols = (2*np.pi)**2 / Adols / 1000\n",
|
||
"uKdols = np.sqrt( (4*np.pi**2 / Adols**2)**2 * uAdols**2 ) / 1000\n",
|
||
"KBdols = (2*np.pi)**2 / Bdols / 1000\n",
|
||
"uKBdols = np.sqrt( (4*np.pi**2 / Bdols**2)**2 * uBdols**2 ) / 1000\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE:\")\n",
|
||
"print(f\"Adols = {Adols:.5f} ± {uAdols:.5f}\")\n",
|
||
"print(f\"Bdols = {Bdols:.5f} ± {uBdols:.5f}\")\n",
|
||
"print(f\"R² = {R2:.5f}\")\n",
|
||
"print(f\"Kdols = {Kdols:.5f} ± {uKdols:.5f}\")\n",
|
||
"print(f\"KBdols = {KBdols:.5f} ± {uKBdols:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 26,
|
||
"id": "a0ba5c8d",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.figure(figsize=(10,6))\n",
|
||
"\n",
|
||
"# Seaborn scatter\n",
|
||
"sns.scatterplot( data=datad,\n",
|
||
" x=\"x\",\n",
|
||
" y=\"y\",\n",
|
||
" s=7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Barre d’errore\n",
|
||
"plt.errorbar(\n",
|
||
" datad[\"x\"],\n",
|
||
" datad[\"y\"],\n",
|
||
" xerr=datad[\"ux\"],\n",
|
||
" yerr=datad[\"uy\"],\n",
|
||
" fmt=\"none\",\n",
|
||
" ecolor=\"gray\",\n",
|
||
" elinewidth=1,\n",
|
||
" capsize=3,\n",
|
||
" alpha=0.7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Linea di regressione\n",
|
||
"xfit = np.linspace(0, datad[\"x\"].max(), 200)\n",
|
||
"yfit = Bdols + Adols * xfit\n",
|
||
"\n",
|
||
"plt.plot(\n",
|
||
" xfit, yfit,\n",
|
||
" color=\"crimson\", linewidth=1, zorder=10, label=\"Fit lineare OLS\"\n",
|
||
")\n",
|
||
"\n",
|
||
"plt.xlim(left=0)\n",
|
||
"plt.ylim(bottom=0)\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.xlabel(\"Meq (g)\")\n",
|
||
"plt.ylabel(\"T^2 (s^2)\")\n",
|
||
"plt.title(\"Legge di ??\")\n",
|
||
"plt.legend()\n",
|
||
"plt.grid(True, linestyle=\"--\", alpha=0.1)\n",
|
||
"\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 27,
|
||
"id": "3c7c05e6",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Chi² = 17.93044\n",
|
||
"GdL = 2\n",
|
||
"Chi² rid = 8.96522\n",
|
||
"P(0, chi²)= 0.99987\n",
|
||
"\n",
|
||
"\n",
|
||
"############################################################\n",
|
||
"capiamo quale dato sta contribuendo maggiormente\n",
|
||
"0 2.355712\n",
|
||
"1 3.797810\n",
|
||
"2 0.836627\n",
|
||
"3 10.940294\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"F_fit = Bdols + Adols * datad[\"x\"]\n",
|
||
"sigma = np.sqrt(datad[\"uy\"]**2 + (Adols * datad[\"ux\"])**2)\n",
|
||
"\n",
|
||
"chi2_val = np.sum( ((datad[\"y\"] - F_fit) / sigma)**2 )\n",
|
||
"\n",
|
||
"N = len(datad)\n",
|
||
"nu = N - 2\n",
|
||
"\n",
|
||
"chi2_red = chi2_val / nu\n",
|
||
"Pdols = chi2.cdf(chi2_val, df=nu)\n",
|
||
"\n",
|
||
"\n",
|
||
"print(f\"Chi² = {chi2_val:.5f}\")\n",
|
||
"print(f\"GdL = {nu}\")\n",
|
||
"print(f\"Chi² rid = {chi2_red:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {Pdols:.5f}\")\n",
|
||
"print(\"\\n\\n\" + \"#\"*60)\n",
|
||
"print(\"capiamo quale dato sta contribuendo maggiormente\")\n",
|
||
"print(((datad[\"y\"] - F_fit) / sigma)**2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a1296a66",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Regressione lineare Carpi"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 28,
|
||
"id": "698e3c48",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Ax + B : \n",
|
||
"AdC = 0.00162 ± 0.00000\n",
|
||
"BdC = 0.01007 ± 0.00011\n",
|
||
"cov_ABdC = -0.000000\n",
|
||
"P(0,chi²)= 0.96181\n",
|
||
"KdC = 24.34964 ± 0.00989\n",
|
||
"KBdC = 3.91877 ± 0.04363\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"def sigma_y_equiv(x, y, sigma_x, sigma_y):\n",
|
||
" # Stima iniziale di A con sola sigma_y\n",
|
||
" sy2 = sigma_y**2\n",
|
||
" Sw = np.sum(1 / sy2)\n",
|
||
" Sx = np.sum(x / sy2)\n",
|
||
" Sxx = np.sum(x**2 / sy2)\n",
|
||
" Sy = np.sum(y / sy2)\n",
|
||
" Sxy = np.sum(x * y / sy2)\n",
|
||
" delta = Sxx * Sw - Sx**2\n",
|
||
" A_est = (Sxy * Sw - Sx * Sy) / delta\n",
|
||
"\n",
|
||
" # Propagazione\n",
|
||
" sigma_eq = np.sqrt(sigma_y**2 + A_est**2 * sigma_x**2)\n",
|
||
" return sigma_eq\n",
|
||
"\n",
|
||
"\n",
|
||
"def reg_lin(x, y, sigma_x, sigma_y):\n",
|
||
" x = np.asarray(x, dtype=float)\n",
|
||
" y = np.asarray(y, dtype=float)\n",
|
||
" sigma_x = np.asarray(sigma_x, dtype=float)\n",
|
||
" sigma_y = np.asarray(sigma_y, dtype=float)\n",
|
||
"\n",
|
||
" # Propagazione errore x → y\n",
|
||
" sigma_y_eq = sigma_y_equiv(x, y, sigma_x, sigma_y)\n",
|
||
"\n",
|
||
" # Somme pesate\n",
|
||
" w = 1.0 / sigma_y_eq**2\n",
|
||
" Sw = np.sum(w)\n",
|
||
" Sx = np.sum(w * x)\n",
|
||
" Sxx = np.sum(w * x**2)\n",
|
||
" Sy = np.sum(w * y)\n",
|
||
" Sxy = np.sum(w * x * y)\n",
|
||
" delta = Sxx * Sw - Sx**2\n",
|
||
"\n",
|
||
" # Parametri\n",
|
||
" A = (Sxy * Sw - Sx * Sy) / delta\n",
|
||
" B = (Sxx * Sy - Sxy * Sx) / delta\n",
|
||
" sigma_A = np.sqrt(Sw / delta)\n",
|
||
" sigma_B = np.sqrt(Sxx / delta)\n",
|
||
" cov_AB = -Sx / delta\n",
|
||
"\n",
|
||
" # Chi quadro\n",
|
||
" x2 = np.sum((y - A * x - B)**2 / sigma_y_eq**2)\n",
|
||
" dof = len(x) - 2\n",
|
||
" chi = sc.stats.chi2.cdf(x2, dof) # P(X² > x2)\n",
|
||
"\n",
|
||
" return A, B, sigma_A, sigma_B, cov_AB, chi\n",
|
||
"\n",
|
||
"\n",
|
||
"AdC, BdC, uAdC, uBdC, covABdC, chidC = reg_lin(datad[\"x\"], datad[\"y\"], datad[\"ux\"], datad[\"uy\"])\n",
|
||
"\n",
|
||
"# Calcolo del K dai parametri\n",
|
||
"KdC = (2*np.pi)**2 / AdC / 1000\n",
|
||
"uKdC = np.sqrt( (4*np.pi**2 / AdC**2)**2 * uAdC**2 ) / 1000\n",
|
||
"KBdC = (2*np.pi)**2 / BdC / 1000\n",
|
||
"uKBdC = np.sqrt( (4*np.pi**2 / BdC**2)**2 * uBdC**2 ) / 1000\n",
|
||
"\n",
|
||
"print(\"Ax + B : \")\n",
|
||
"print(f\"AdC = {AdC:.5f} ± {uAdC:.5f}\")\n",
|
||
"print(f\"BdC = {BdC:.5f} ± {uBdC:.5f}\")\n",
|
||
"print(f\"cov_ABdC = {covABdC:.6f}\")\n",
|
||
"print(f\"P(0,chi²)= {chidC:.5f}\")\n",
|
||
"print(f\"KdC = {KdC:.5f} ± {uKdC:.5f}\")\n",
|
||
"print(f\"KBdC = {KBdC:.5f} ± {uKBdC:.5f}\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 29,
|
||
"id": "a0ab8534",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.figure(figsize=(10,6))\n",
|
||
"\n",
|
||
"# Seaborn scatter\n",
|
||
"sns.scatterplot(\n",
|
||
" data=datad,\n",
|
||
" x=\"x\",\n",
|
||
" y=\"y\",\n",
|
||
" s=7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Barre d’errore\n",
|
||
"plt.errorbar(\n",
|
||
" datad[\"x\"],\n",
|
||
" datad[\"y\"],\n",
|
||
" xerr=datad[\"ux\"],\n",
|
||
" yerr=datad[\"uy\"],\n",
|
||
" fmt=\"none\",\n",
|
||
" ecolor=\"gray\",\n",
|
||
" elinewidth=1,\n",
|
||
" capsize=3,\n",
|
||
" alpha=0.7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Linea di regressione\n",
|
||
"xfit = np.linspace(0, datad[\"x\"].max(), 200)\n",
|
||
"yfit = BdC + AdC * xfit\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.plot(\n",
|
||
" xfit,\n",
|
||
" yfit,\n",
|
||
" color=\"crimson\",\n",
|
||
" linewidth=1,\n",
|
||
" zorder=10,\n",
|
||
" label=\"Fit lineare Carpi\"\n",
|
||
")\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.xlim(left=0)\n",
|
||
"plt.ylim(bottom=0)\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.xlabel(\"Meq (g)\")\n",
|
||
"plt.ylabel(\"T^2 (s^2)\")\n",
|
||
"plt.title(\"Legge di ??\")\n",
|
||
"plt.legend()\n",
|
||
"plt.grid(True, linestyle=\"--\", alpha=0.1)\n",
|
||
"\n",
|
||
"plt.show()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 30,
|
||
"id": "12bb0479",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Chi² = 6.53021\n",
|
||
"GdL = 2\n",
|
||
"Chi² rid = 3.26511\n",
|
||
"P(0, chi²)= 0.96181\n",
|
||
"\n",
|
||
"\n",
|
||
"############################################################\n",
|
||
"capiamo quale dato sta contribuendo maggiormente\n",
|
||
"0 1.366019\n",
|
||
"1 5.154390\n",
|
||
"2 0.000185\n",
|
||
"3 0.009620\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"F_fit = BdC + AdC * datad[\"x\"]\n",
|
||
"sigma = np.sqrt(datad[\"uy\"]**2 + (AdC * datad[\"ux\"])**2)\n",
|
||
"\n",
|
||
"\n",
|
||
"chi2_val = np.sum( ((datad[\"y\"] - F_fit) / sigma)**2 )\n",
|
||
"\n",
|
||
"N = len(datad)\n",
|
||
"nu = N - 2\n",
|
||
"\n",
|
||
"chi2_red = chi2_val / nu\n",
|
||
"PdC = chi2.cdf(chi2_val, df=nu)\n",
|
||
"\n",
|
||
"\n",
|
||
"print(f\"Chi² = {chi2_val:.5f}\")\n",
|
||
"print(f\"GdL = {nu}\")\n",
|
||
"print(f\"Chi² rid = {chi2_red:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {PdC:.5f}\")\n",
|
||
"print(\"\\n\\n\" + \"#\"*60)\n",
|
||
"print(\"capiamo quale dato sta contribuendo maggiormente\")\n",
|
||
"print(((datad[\"y\"] - F_fit) / sigma)**2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "f3bf75d6",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Regressione lineare pesata Yorkfit"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 31,
|
||
"id": "385db415",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"AdY = 0.0016213 ± 0.0000007\n",
|
||
"BdY = 0.0100742 ± 0.0001122\n",
|
||
"cov_ABdY = -7.370190718014568e-11\n",
|
||
"chi² = 6.53021\n",
|
||
"chi² rid = 3.26511\n",
|
||
"P(0, chi²)= 0.96181\n",
|
||
"KdY = 24.34964 ± 0.00989\n",
|
||
"KBdY = 3.91877 ± 0.04363\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"def york_fit(x, y, sx, sy, max_iter=50, tol=1e-15):\n",
|
||
" # Pesi iniziali\n",
|
||
" wx = 1 / sx**2\n",
|
||
" wy = 1 / sy**2\n",
|
||
"\n",
|
||
" # Stima iniziale della pendenza (OLS y|x)\n",
|
||
" A = np.cov(x, y, aweights=wy)[0,1] / np.cov(x, x, aweights=wy)[0,1]\n",
|
||
"\n",
|
||
" for _ in range(max_iter):\n",
|
||
" A_old = A\n",
|
||
"\n",
|
||
" # 1) Pesi combinati\n",
|
||
" Wi = (wx * wy) / (A**2 * wy + wx)\n",
|
||
"\n",
|
||
" # 2) x e y pesati (eq. 10)\n",
|
||
" X_bar = np.sum(Wi * x) / np.sum(Wi)\n",
|
||
" Y_bar = np.sum(Wi * y) / np.sum(Wi)\n",
|
||
"\n",
|
||
" # 3) Variabili centrate\n",
|
||
" Ui = x - X_bar\n",
|
||
" Vi = y - Y_bar\n",
|
||
"\n",
|
||
" # 4) beta\n",
|
||
" beta_i = Wi * (Ui / wy + A * Vi / wx)\n",
|
||
"\n",
|
||
" # 5) Aggiornamento pendenza\n",
|
||
" A = np.sum(Wi * beta_i * Vi) / np.sum(Wi * beta_i * Ui)\n",
|
||
"\n",
|
||
" # Convergenza\n",
|
||
" if abs(A - A_old) < tol:\n",
|
||
" break\n",
|
||
"\n",
|
||
" # 6) Intercetta\n",
|
||
" B = Y_bar - A * X_bar\n",
|
||
"\n",
|
||
" # S = somma Wi (xi - x)**2\n",
|
||
" S = np.sum(Wi * Ui**2)\n",
|
||
"\n",
|
||
" sA = np.sqrt(1 / S)\n",
|
||
" sB = np.sqrt(1 / np.sum(Wi) + X_bar**2 * sA**2)\n",
|
||
"\n",
|
||
" # cov(A,B)\n",
|
||
" cov_AB = -X_bar * sA**2\n",
|
||
"\n",
|
||
" # CHI QUADRATO\n",
|
||
" chi2 = np.sum(Wi * (Vi - A * Ui)**2)\n",
|
||
" dof = len(x) - 2\n",
|
||
" chi2_red = chi2 / dof\n",
|
||
"\n",
|
||
" return A, B, sA, sB, cov_AB, chi2, chi2_red\n",
|
||
"\n",
|
||
"AdY, BdY, uAdY, uBdY, cov_ABdY, chi2_val, chi2_red = york_fit(datad.x, datad.y, datad.ux, datad.uy)\n",
|
||
"PdY = chi2.cdf(chi2_val, df=nu)\n",
|
||
"\n",
|
||
"# Calcolo del K dai parametri\n",
|
||
"KdY = (2*np.pi)**2 / AdY / 1000\n",
|
||
"uKdY = np.sqrt( (4*np.pi**2 / AdY**2)**2 * uAdY**2 ) / 1000\n",
|
||
"KBdY = (2*np.pi)**2 / BdY / 1000\n",
|
||
"uKBdY = np.sqrt( (4*np.pi**2 / BdY**2)**2 * uBdY**2 ) / 1000\n",
|
||
"\n",
|
||
"\n",
|
||
"print(f\"AdY = {AdY:.7f} ± {uAdY:.7f}\")\n",
|
||
"print(f\"BdY = {BdY:.7f} ± {uBdY:.7f}\")\n",
|
||
"print(f\"cov_ABdY = {cov_ABdY}\")\n",
|
||
"print(f\"chi² = {chi2_val:.5f}\")\n",
|
||
"print(f\"chi² rid = {chi2_red:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {PdY:.5f}\")\n",
|
||
"print(f\"KdY = {KdY:.5f} ± {uKdY:.5f}\")\n",
|
||
"print(f\"KBdY = {KBdY:.5f} ± {uKBdY:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 32,
|
||
"id": "698bc57c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.figure(figsize=(10,6))\n",
|
||
"\n",
|
||
"# Seaborn scatter\n",
|
||
"sns.scatterplot(\n",
|
||
" data=datad,\n",
|
||
" x=\"x\",\n",
|
||
" y=\"y\",\n",
|
||
" s=7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Barre d’errore\n",
|
||
"plt.errorbar(\n",
|
||
" datad[\"x\"],\n",
|
||
" datad[\"y\"],\n",
|
||
" xerr=datad[\"ux\"],\n",
|
||
" yerr=datad[\"uy\"],\n",
|
||
" fmt=\"none\",\n",
|
||
" ecolor=\"gray\",\n",
|
||
" elinewidth=1,\n",
|
||
" capsize=3,\n",
|
||
" alpha=0.7\n",
|
||
")\n",
|
||
"\n",
|
||
"# Linea di regressione\n",
|
||
"xfit = np.linspace(0, datad[\"x\"].max(), 200)\n",
|
||
"yfit = BdY + AdY * xfit\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.plot(\n",
|
||
" xfit,\n",
|
||
" yfit,\n",
|
||
" color=\"crimson\",\n",
|
||
" linewidth=1,\n",
|
||
" zorder=10,\n",
|
||
" label=\"Fit lineare York\"\n",
|
||
")\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.xlim(left=0)\n",
|
||
"plt.ylim(bottom=0)\n",
|
||
"\n",
|
||
"\n",
|
||
"plt.xlabel(\"Meq (g)\")\n",
|
||
"plt.ylabel(\"T^2 (s^2)\")\n",
|
||
"plt.title(\"Legge di ??\")\n",
|
||
"plt.legend()\n",
|
||
"plt.grid(True, linestyle=\"--\", alpha=0.1)\n",
|
||
"\n",
|
||
"plt.show()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "2e612bc6",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Raccolta finale di dati dinamici"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 33,
|
||
"id": "fc32f9e6",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"RISULTATI senza ERRORE STRUMENTALE INCLUSO:\n",
|
||
"Media pesata K = 23.49313 ± 0.00063\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE OLS:\n",
|
||
"Adols = 0.00162 ± 0.00000\n",
|
||
"Bdols = 0.01007 ± 0.00034\n",
|
||
"P(0,chi²)= 0.99987\n",
|
||
"Kdols = 24.35158 ± 0.03547\n",
|
||
"KBdols = 3.92000 ± 0.13366\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE Carpi:\n",
|
||
"AdC = 0.00162 ± 0.00000\n",
|
||
"BdC = 0.01007 ± 0.00011\n",
|
||
"P(0,chi²)= 0.96181\n",
|
||
"KdC = 24.34964 ± 0.00989\n",
|
||
"KBdC = 3.91877 ± 0.04363\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE York:\n",
|
||
"Ady = 0.00162 ± 0.00000\n",
|
||
"Bdy = 0.01007 ± 0.00011\n",
|
||
"P(0,chi²)= 0.96181\n",
|
||
"KdY = 24.34964 ± 0.00989\n",
|
||
"KBdY = 3.91877 ± 0.04363\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(\"RISULTATI senza ERRORE STRUMENTALE INCLUSO:\")\n",
|
||
"print(f\"Media pesata K = {KdM:.5f} ± {uKdM:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE OLS:\")\n",
|
||
"print(f\"Adols = {Adols:.5f} ± {uAdols:.5f}\")\n",
|
||
"print(f\"Bdols = {Bdols:.5f} ± {uBdols:.5f}\")\n",
|
||
"print(f\"P(0,chi²)= {Pdols:.5f}\")\n",
|
||
"print(f\"Kdols = {Kdols:.5f} ± {uKdols:.5f}\")\n",
|
||
"print(f\"KBdols = {KBdols:.5f} ± {uKBdols:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE Carpi:\")\n",
|
||
"print(f\"AdC = {AdC:.5f} ± {uAdC:.5f}\")\n",
|
||
"print(f\"BdC = {BdC:.5f} ± {uBdC:.5f}\")\n",
|
||
"print(f\"P(0,chi²)= {PdC:.5f}\")\n",
|
||
"print(f\"KdC = {KdC:.5f} ± {uKdC:.5f}\")\n",
|
||
"print(f\"KBdC = {KBdC:.5f} ± {uKBdC:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE York:\")\n",
|
||
"print(f\"Ady = {AdY:.5f} ± {uAdY:.5f}\")\n",
|
||
"print(f\"Bdy = {BdY:.5f} ± {uBdY:.5f}\")\n",
|
||
"print(f\"P(0,chi²)= {PdY:.5f}\")\n",
|
||
"print(f\"KdY = {KdY:.5f} ± {uKdY:.5f}\")\n",
|
||
"print(f\"KBdY = {KBdY:.5f} ± {uKBdY:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "7caf197a",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Aggiunta degli errori strumentali"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 34,
|
||
"id": "f4897de3",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"res_T = 0.001000\n",
|
||
"res_T2 = 0.001080\n",
|
||
"res_b = 0.004082\n",
|
||
"res_uAd = 0.000009\n",
|
||
"uKd_strum= 0.132923\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"res_b = 0.01 / np.sqrt(6) # riso bilancia\n",
|
||
"res_T = 0.001 # riso T\n",
|
||
"\n",
|
||
"T = 2 * np.pi / df.w\n",
|
||
"res_T2 = np.max(2 * T * res_T)\n",
|
||
"\n",
|
||
"res_uAd = np.max(np.sqrt( (1 / Meq)**2 * res_T2**2 + (T2 / Meq**2)**2 * res_b**2))\n",
|
||
"\n",
|
||
"uKd_strum = np.max(np.abs(4 * np.pi**2 / Ad**2) * res_uAd) / 1000\n",
|
||
"\n",
|
||
"print(f\"res_T = {res_T:.6f}\")\n",
|
||
"print(f\"res_T2 = {res_T2:.6f}\")\n",
|
||
"print(f\"res_b = {res_b:.6f}\")\n",
|
||
"print(f\"res_uAd = {res_uAd:.6f}\")\n",
|
||
"print(f\"uKd_strum= {uKd_strum:.6f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 35,
|
||
"id": "37d88464",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"uKdM_fin = np.sqrt(uKdM**2 + uKd_strum**2)\n",
|
||
"\n",
|
||
"uAdols_fin = np.sqrt(uAdols**2 + res_uAd**2)\n",
|
||
"uBdols_fin = np.sqrt(uBdols**2 + res_uAd**2)\n",
|
||
"uKdols_fin = np.sqrt(uKdols**2 + uKd_strum**2)\n",
|
||
"\n",
|
||
"uAdC_fin = np.sqrt(uAdC**2 + res_uAd**2)\n",
|
||
"uBdC_fin = np.sqrt(uBdC**2 + res_uAd**2)\n",
|
||
"uKdC_fin = np.sqrt(uKdC**2 + uKd_strum**2)\n",
|
||
"\n",
|
||
"uAdY_fin = np.sqrt(uAdY**2 + res_uAd**2)\n",
|
||
"uBdY_fin = np.sqrt(uBdY**2 + res_uAd**2)\n",
|
||
"uKdY_fin = np.sqrt(uKdY**2 + uKd_strum**2)\n",
|
||
"\n",
|
||
"\n",
|
||
"uy_fin_d = np.sqrt(datad[\"uy\"]**2 + res_T2**2)\n",
|
||
"ux_fin_d = np.sqrt(datad[\"ux\"]**2 + res_b**2)\n",
|
||
"\n",
|
||
"GdLd = len(datad) - 2\n",
|
||
"\n",
|
||
"\n",
|
||
"F_fit_dols = Bdols + Adols * datad[\"x\"]\n",
|
||
"sigma_dols = np.sqrt(uy_fin_d**2 + (Adols * ux_fin_d)**2)\n",
|
||
"chi2_dols = np.sum(((datad[\"y\"] - F_fit_dols) / sigma_dols)**2)\n",
|
||
"\n",
|
||
"F_fit_dC = BdC + AdC * datad[\"x\"]\n",
|
||
"sigma_dC = np.sqrt(uy_fin_d**2 + (AdC * ux_fin_d)**2)\n",
|
||
"chi2_dC = np.sum(((datad[\"y\"] - F_fit_dC) / sigma_dC)**2)\n",
|
||
"\n",
|
||
"F_fit_dY = BdY + AdY * datad[\"x\"]\n",
|
||
"sigma_dY = np.sqrt(uy_fin_d**2 + (AdY * ux_fin_d)**2)\n",
|
||
"chi2_dY = np.sum(((datad[\"y\"] - F_fit_dY) / sigma_dY)**2)\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "42c27c50",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Risultati sulla propagazione dell'errore"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 36,
|
||
"id": "9075e52d",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"RISULTATI CON ERRORE STRUMENTALE INCLUSO:\n",
|
||
"Media pesata Kd = 23.49313 ± 0.13292\n",
|
||
"\n",
|
||
"RISULTATI OLS:\n",
|
||
"Adols = 0.00162 ± 0.00001\n",
|
||
"Bdols = 0.01007 ± 0.00034\n",
|
||
"Kdols = 24.35158 ± 0.13757\n",
|
||
"Chi² = 0.01897 | rid = 0.00949 | P = 0.00944\n",
|
||
"\n",
|
||
"RISULTATI Carpi:\n",
|
||
"AdC = 0.00162 ± 0.00001\n",
|
||
"BdC = 0.01007 ± 0.00011\n",
|
||
"KdC = 24.34964 ± 0.13329\n",
|
||
"Chi² = 0.02061 | rid = 0.01030 | P = 0.01025\n",
|
||
"\n",
|
||
"RISULTATI York:\n",
|
||
"AdY = 0.00162 ± 0.00001\n",
|
||
"BdY = 0.01007 ± 0.00011\n",
|
||
"KdY = 24.34964 ± 0.13329\n",
|
||
"Chi² = 0.02061 | rid = 0.01030 | P = 0.01025\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(\"RISULTATI CON ERRORE STRUMENTALE INCLUSO:\")\n",
|
||
"print(f\"Media pesata Kd = {KdM:.5f} ± {uKdM_fin:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI OLS:\")\n",
|
||
"print(f\"Adols = {Adols:.5f} ± {uAdols_fin:.5f}\")\n",
|
||
"print(f\"Bdols = {Bdols:.5f} ± {uBdols_fin:.5f}\")\n",
|
||
"print(f\"Kdols = {Kdols:.5f} ± {uKdols_fin:.5f}\")\n",
|
||
"print(f\"Chi² = {chi2_dols:.5f} | rid = {chi2_dols/GdLd:.5f} | P = {chi2.cdf(chi2_dols, GdLd):.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI Carpi:\")\n",
|
||
"print(f\"AdC = {AdC:.5f} ± {uAdC_fin:.5f}\")\n",
|
||
"print(f\"BdC = {BdC:.5f} ± {uBdC_fin:.5f}\")\n",
|
||
"print(f\"KdC = {KdC:.5f} ± {uKdC_fin:.5f}\")\n",
|
||
"print(f\"Chi² = {chi2_dC:.5f} | rid = {chi2_dC/GdLd:.5f} | P = {chi2.cdf(chi2_dC, GdLd):.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI York:\")\n",
|
||
"print(f\"AdY = {AdY:.5f} ± {uAdY_fin:.5f}\")\n",
|
||
"print(f\"BdY = {BdY:.5f} ± {uBdY_fin:.5f}\")\n",
|
||
"print(f\"KdY = {KdY:.5f} ± {uKdY_fin:.5f}\")\n",
|
||
"print(f\"Chi² = {chi2_dY:.5f} | rid = {chi2_dY/GdLd:.5f} | P = {chi2.cdf(chi2_dY, GdLd):.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "6f4edfa1",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Dinamica Cronometro"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 37,
|
||
"id": "0f407f81",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"0 NaN\n",
|
||
"1 NaN\n",
|
||
"2 NaN\n",
|
||
"3 NaN\n",
|
||
"Name: t, dtype: float64\n",
|
||
"0 NaN\n",
|
||
"1 NaN\n",
|
||
"2 NaN\n",
|
||
"3 NaN\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"T2t = (df.t / 20)**2\n",
|
||
"uT2t = 2 * (df.t / 20) * (df.ut / 20)\n",
|
||
"\n",
|
||
"print(T2t)\n",
|
||
"print(uT2t)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "8d097869",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Calcolo dei K e media pesata"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 38,
|
||
"id": "99bc83a7",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"0 NaN\n",
|
||
"1 NaN\n",
|
||
"2 NaN\n",
|
||
"3 NaN\n",
|
||
"dtype: float64\n",
|
||
"0 NaN\n",
|
||
"1 NaN\n",
|
||
"2 NaN\n",
|
||
"3 NaN\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"Adt = T2t / Meq\n",
|
||
"uAdt = np.sqrt( (1/Meq)**2 * uT2t**2 + (T2t/Meq**2)**2 * uMeq**2 )\n",
|
||
"\n",
|
||
"Kdt = 4 * np.pi**2 / Adt\n",
|
||
"uKdt = (4 * np.pi**2 / Adt**2) * uAdt\n",
|
||
"\n",
|
||
"Kdt\n",
|
||
"uKdt\n",
|
||
"\n",
|
||
"print(Kdt)\n",
|
||
"print(uKdt)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 39,
|
||
"id": "ae55d12a",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"K-medio (t): nan\n",
|
||
"sigmaC (t): inf\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/tmp/ipykernel_299408/2995330097.py:10: RuntimeWarning: invalid value encountered in scalar divide\n",
|
||
" media = num / den\n",
|
||
"/tmp/ipykernel_299408/2995330097.py:11: RuntimeWarning: divide by zero encountered in scalar divide\n",
|
||
" sigma = np.sqrt(1.0 / den)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"KdtM, uKdtM = mediaPesata(Kdt, uKdt)\n",
|
||
"KdtM /= 1e3\n",
|
||
"uKdtM /= 1e3\n",
|
||
"print(\"K-medio (t):\", KdtM)\n",
|
||
"print(\"sigmaC (t):\", uKdtM)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "634a06e9",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Analisi con regressioni e grafici"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 40,
|
||
"id": "75e94b0a",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"datat = pd.DataFrame({\n",
|
||
" \"x\": Meq,\n",
|
||
" \"ux\": uMeq,\n",
|
||
" \"y\": T2t,\n",
|
||
" \"uy\": uT2t\n",
|
||
"})"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "e7761130",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Regressione lineare \"OLS\"\n",
|
||
"Non tiene conto dei nostri errori, un risultato puro e semplice"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 41,
|
||
"id": "896388e2",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" OLS Regression Results \n",
|
||
"==============================================================================\n",
|
||
"Dep. Variable: y R-squared: nan\n",
|
||
"Model: OLS Adj. R-squared: nan\n",
|
||
"Method: Least Squares F-statistic: nan\n",
|
||
"Date: Sun, 05 Apr 2026 Prob (F-statistic): nan\n",
|
||
"Time: 21:57:07 Log-Likelihood: nan\n",
|
||
"No. Observations: 4 AIC: nan\n",
|
||
"Df Residuals: 2 BIC: nan\n",
|
||
"Df Model: 1 \n",
|
||
"Covariance Type: nonrobust \n",
|
||
"==============================================================================\n",
|
||
" coef std err t P>|t| [0.025 0.975]\n",
|
||
"------------------------------------------------------------------------------\n",
|
||
"const nan nan nan nan nan nan\n",
|
||
"x nan nan nan nan nan nan\n",
|
||
"==============================================================================\n",
|
||
"Omnibus: nan Durbin-Watson: nan\n",
|
||
"Prob(Omnibus): nan Jarque-Bera (JB): nan\n",
|
||
"Skew: nan Prob(JB): nan\n",
|
||
"Kurtosis: nan Cond. No. 948.\n",
|
||
"==============================================================================\n",
|
||
"\n",
|
||
"Notes:\n",
|
||
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE OLS (t):\n",
|
||
"Atols = nan ± nan\n",
|
||
"Btols = nan ± nan\n",
|
||
"R² = nan\n",
|
||
"Kdtols = nan ± nan\n",
|
||
"KBdtols = nan ± nan\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/home/jack/uni/lab/.venv/lib/python3.13/site-packages/statsmodels/stats/stattools.py:74: ValueWarning: omni_normtest is not valid with less than 8 observations; 4 samples were given.\n",
|
||
" warn(\"omni_normtest is not valid with less than 8 observations; %i \"\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"X = sm.add_constant(datat[\"x\"])\n",
|
||
"model = sm.OLS(datat[\"y\"], X).fit()\n",
|
||
"\n",
|
||
"print(model.summary())\n",
|
||
"\n",
|
||
"Btols = model.params[\"const\"]\n",
|
||
"Atols = model.params[\"x\"]\n",
|
||
"uBtols = model.bse[\"const\"]\n",
|
||
"uAtols = model.bse[\"x\"]\n",
|
||
"R2t = model.rsquared\n",
|
||
"\n",
|
||
"Kdtols = 4 * np.pi**2 / Atols / 1000\n",
|
||
"uKdtols = (4 * np.pi**2 / Atols**2) * uAtols / 1000\n",
|
||
"KBdtols = 4 * np.pi**2 / Btols / 1000\n",
|
||
"uKBdtols = (4 * np.pi**2 / Btols**2) * uBtols / 1000\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE OLS (t):\")\n",
|
||
"print(f\"Atols = {Atols:.5f} ± {uAtols:.5f}\")\n",
|
||
"print(f\"Btols = {Btols:.5f} ± {uBtols:.5f}\")\n",
|
||
"print(f\"R² = {R2t:.5f}\")\n",
|
||
"print(f\"Kdtols = {Kdtols:.5f} ± {uKdtols:.5f}\")\n",
|
||
"print(f\"KBdtols = {KBdtols:.5f} ± {uKBdtols:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 42,
|
||
"id": "61e40e4c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.figure(figsize=(10,6))\n",
|
||
"\n",
|
||
"sns.scatterplot(data=datat, x=\"x\", y=\"y\", s=7)\n",
|
||
"\n",
|
||
"plt.errorbar(\n",
|
||
" datat[\"x\"], datat[\"y\"],\n",
|
||
" xerr=datat[\"ux\"], yerr=datat[\"uy\"],\n",
|
||
" fmt=\"none\", ecolor=\"gray\", elinewidth=1, capsize=3, alpha=0.7\n",
|
||
")\n",
|
||
"\n",
|
||
"xfit = np.linspace(0, datat[\"x\"].max(), 200)\n",
|
||
"yfit = Btols + Atols * xfit\n",
|
||
"\n",
|
||
"plt.plot(xfit, yfit, color=\"crimson\", linewidth=1, zorder=10, label=\"Fit OLS t\")\n",
|
||
"plt.xlim(left=0)\n",
|
||
"plt.ylim(bottom=0)\n",
|
||
"plt.xlabel(\"Meq (g)\")\n",
|
||
"plt.ylabel(\"T² (s²)\")\n",
|
||
"plt.title(\"Legge di ?? — cronometro\")\n",
|
||
"plt.legend()\n",
|
||
"plt.grid(True, linestyle=\"--\", alpha=0.1)\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 43,
|
||
"id": "354687ec",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Chi² = 0.00000\n",
|
||
"GdL = 2\n",
|
||
"Chi² rid = 0.00000\n",
|
||
"P(0, chi²)= 0.00000\n",
|
||
"\n",
|
||
"\n",
|
||
"############################################################\n",
|
||
"capiamo quale dato sta contribuendo maggiormente\n",
|
||
"0 NaN\n",
|
||
"1 NaN\n",
|
||
"2 NaN\n",
|
||
"3 NaN\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"F_fit = Btols + Atols * datat[\"x\"]\n",
|
||
"sigma = np.sqrt(datat[\"uy\"]**2 + (Atols * datat[\"ux\"])**2)\n",
|
||
"\n",
|
||
"chi2_val = np.sum(((datat[\"y\"] - F_fit) / sigma)**2)\n",
|
||
"\n",
|
||
"N = len(datat)\n",
|
||
"nut = N - 2\n",
|
||
"\n",
|
||
"chi2_red = chi2_val / nut\n",
|
||
"Ptols = chi2.cdf(chi2_val, df=nut)\n",
|
||
"\n",
|
||
"print(f\"Chi² = {chi2_val:.5f}\")\n",
|
||
"print(f\"GdL = {nut}\")\n",
|
||
"print(f\"Chi² rid = {chi2_red:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {Ptols:.5f}\")\n",
|
||
"print(\"\\n\\n\" + \"#\"*60)\n",
|
||
"print(\"capiamo quale dato sta contribuendo maggiormente\")\n",
|
||
"print(((datat[\"y\"] - F_fit) / sigma)**2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c28f2d34",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Regressione lineare Carpi"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 44,
|
||
"id": "8d6cd1df",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Ax + B (Carpi, t):\n",
|
||
"AtC = nan ± nan\n",
|
||
"BtC = nan ± nan\n",
|
||
"cov_ABtC = nan\n",
|
||
"P(0,chi²)= nan\n",
|
||
"KdtC = nan ± nan\n",
|
||
"KBdtC = nan ± nan\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"AtC, BtC, uAtC, uBtC, covABtC, chitC = reg_lin(datat[\"x\"], datat[\"y\"], datat[\"ux\"], datat[\"uy\"])\n",
|
||
"\n",
|
||
"KdtC = 4 * np.pi**2 / AtC / 1000\n",
|
||
"uKdtC = (4 * np.pi**2 / AtC**2) * uAtC / 1000\n",
|
||
"KBdtC = 4 * np.pi**2 / BtC / 1000\n",
|
||
"uKBdtC = (4 * np.pi**2 / BtC**2) * uBtC / 1000\n",
|
||
"\n",
|
||
"print(\"Ax + B (Carpi, t):\")\n",
|
||
"print(f\"AtC = {AtC:.5f} ± {uAtC:.5f}\")\n",
|
||
"print(f\"BtC = {BtC:.5f} ± {uBtC:.5f}\")\n",
|
||
"print(f\"cov_ABtC = {covABtC:.6f}\")\n",
|
||
"print(f\"P(0,chi²)= {chitC:.5f}\")\n",
|
||
"print(f\"KdtC = {KdtC:.5f} ± {uKdtC:.5f}\")\n",
|
||
"print(f\"KBdtC = {KBdtC:.5f} ± {uKBdtC:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 45,
|
||
"id": "592c257c",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.figure(figsize=(10,6))\n",
|
||
"\n",
|
||
"sns.scatterplot(data=datat, x=\"x\", y=\"y\", s=7)\n",
|
||
"\n",
|
||
"plt.errorbar(\n",
|
||
" datat[\"x\"], datat[\"y\"],\n",
|
||
" xerr=datat[\"ux\"], yerr=datat[\"uy\"],\n",
|
||
" fmt=\"none\", ecolor=\"gray\", elinewidth=1, capsize=3, alpha=0.7\n",
|
||
")\n",
|
||
"\n",
|
||
"xfit = np.linspace(0, datat[\"x\"].max(), 200)\n",
|
||
"yfit = BtC + AtC * xfit\n",
|
||
"\n",
|
||
"plt.plot(xfit, yfit, color=\"crimson\", linewidth=1, zorder=10, label=\"Fit Carpi (t)\")\n",
|
||
"plt.xlim(left=0)\n",
|
||
"plt.ylim(bottom=0)\n",
|
||
"plt.xlabel(\"Meq (g)\")\n",
|
||
"plt.ylabel(\"T² (s²)\")\n",
|
||
"plt.title(\"Legge di Hooke dinamica — cronometro\")\n",
|
||
"plt.legend()\n",
|
||
"plt.grid(True, linestyle=\"--\", alpha=0.1)\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 46,
|
||
"id": "12f276cc",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Chi² = 0.00000\n",
|
||
"GdL = 2\n",
|
||
"Chi² rid = 0.00000\n",
|
||
"P(0, chi²)= 0.00000\n",
|
||
"\n",
|
||
"\n",
|
||
"############################################################\n",
|
||
"capiamo quale dato sta contribuendo maggiormente\n",
|
||
"0 NaN\n",
|
||
"1 NaN\n",
|
||
"2 NaN\n",
|
||
"3 NaN\n",
|
||
"dtype: float64\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"F_fit = BtC + AtC * datat[\"x\"]\n",
|
||
"sigma = np.sqrt(datat[\"uy\"]**2 + (AtC * datat[\"ux\"])**2)\n",
|
||
"chi2_val = np.sum(((datat[\"y\"] - F_fit) / sigma)**2)\n",
|
||
"chi2_red = chi2_val / nut\n",
|
||
"PtC = chi2.cdf(chi2_val, df=nut)\n",
|
||
"\n",
|
||
"print(f\"Chi² = {chi2_val:.5f}\")\n",
|
||
"print(f\"GdL = {nut}\")\n",
|
||
"print(f\"Chi² rid = {chi2_red:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {PtC:.5f}\")\n",
|
||
"print(\"\\n\\n\" + \"#\"*60)\n",
|
||
"print(\"capiamo quale dato sta contribuendo maggiormente\")\n",
|
||
"print(((datat[\"y\"] - F_fit) / sigma)**2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "0823cca1",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Regressione lineare pesata Yorkfit"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 47,
|
||
"id": "d04ee20e",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"AtY = nan ± inf\n",
|
||
"BtY = nan ± nan\n",
|
||
"cov_ABtY = nan\n",
|
||
"chi² = 0.00000\n",
|
||
"chi² rid = 0.00000\n",
|
||
"P(0, chi²)= 0.00000\n",
|
||
"KdtY = nan ± nan\n",
|
||
"KBdtY = nan ± nan\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/tmp/ipykernel_299408/788188722.py:16: RuntimeWarning: invalid value encountered in scalar divide\n",
|
||
" X_bar = np.sum(Wi * x) / np.sum(Wi)\n",
|
||
"/tmp/ipykernel_299408/788188722.py:17: RuntimeWarning: invalid value encountered in scalar divide\n",
|
||
" Y_bar = np.sum(Wi * y) / np.sum(Wi)\n",
|
||
"/tmp/ipykernel_299408/788188722.py:27: RuntimeWarning: invalid value encountered in scalar divide\n",
|
||
" A = np.sum(Wi * beta_i * Vi) / np.sum(Wi * beta_i * Ui)\n",
|
||
"/tmp/ipykernel_299408/788188722.py:39: RuntimeWarning: divide by zero encountered in scalar divide\n",
|
||
" sA = np.sqrt(1 / S)\n",
|
||
"/tmp/ipykernel_299408/788188722.py:40: RuntimeWarning: divide by zero encountered in scalar divide\n",
|
||
" sB = np.sqrt(1 / np.sum(Wi) + X_bar**2 * sA**2)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"AtY, BtY, uAtY, uBtY, cov_ABtY, chi2_val_t, chi2_red_t = york_fit(datat.x, datat.y, datat.ux, datat.uy)\n",
|
||
"PtY = chi2.cdf(chi2_val_t, df=nut)\n",
|
||
"\n",
|
||
"KdtY = 4 * np.pi**2 / AtY / 1000\n",
|
||
"uKdtY = (4 * np.pi**2 / AtY**2) * uAtY / 1000\n",
|
||
"KBdtY = 4 * np.pi**2 / BtY / 1000\n",
|
||
"uKBdtY = (4 * np.pi**2 / BtY**2) * uBtY / 1000\n",
|
||
"\n",
|
||
"print(f\"AtY = {AtY:.7f} ± {uAtY:.7f}\")\n",
|
||
"print(f\"BtY = {BtY:.7f} ± {uBtY:.7f}\")\n",
|
||
"print(f\"cov_ABtY = {cov_ABtY}\")\n",
|
||
"print(f\"chi² = {chi2_val_t:.5f}\")\n",
|
||
"print(f\"chi² rid = {chi2_red_t:.5f}\")\n",
|
||
"print(f\"P(0, chi²)= {PtY:.5f}\")\n",
|
||
"print(f\"KdtY = {KdtY:.5f} ± {uKdtY:.5f}\")\n",
|
||
"print(f\"KBdtY = {KBdtY:.5f} ± {uKBdtY:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 48,
|
||
"id": "e795e732",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 1000x600 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"plt.figure(figsize=(10,6))\n",
|
||
"\n",
|
||
"sns.scatterplot(data=datat, x=\"x\", y=\"y\", s=7)\n",
|
||
"\n",
|
||
"plt.errorbar(\n",
|
||
" datat[\"x\"], datat[\"y\"],\n",
|
||
" xerr=datat[\"ux\"], yerr=datat[\"uy\"],\n",
|
||
" fmt=\"none\", ecolor=\"gray\", elinewidth=1, capsize=3, alpha=0.7\n",
|
||
")\n",
|
||
"\n",
|
||
"xfit = np.linspace(0, datat[\"x\"].max(), 200)\n",
|
||
"yfit = BtY + AtY * xfit\n",
|
||
"\n",
|
||
"plt.plot(xfit, yfit, color=\"crimson\", linewidth=1, zorder=10, label=\"Fit York (t)\")\n",
|
||
"plt.xlim(left=0)\n",
|
||
"plt.ylim(bottom=0)\n",
|
||
"plt.xlabel(\"Meq (g)\")\n",
|
||
"plt.ylabel(\"T² (s²)\")\n",
|
||
"plt.title(\"Legge di Hooke dinamica — cronometro\")\n",
|
||
"plt.legend()\n",
|
||
"plt.grid(True, linestyle=\"--\", alpha=0.1)\n",
|
||
"plt.show()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "038b2684",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Raccolta finale di dati dinamici col cronometro"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 49,
|
||
"id": "46ef07bd",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"RISULTATI senza ERRORE STRUMENTALE (cronometro):\n",
|
||
"Media pesata K = nan ± inf\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE OLS:\n",
|
||
"Atols = nan ± nan\n",
|
||
"Btols = nan ± nan\n",
|
||
"P(0,chi²)= 0.00000\n",
|
||
"Kdtols = nan ± nan\n",
|
||
"KBdtols = nan ± nan\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE Carpi:\n",
|
||
"AtC = nan ± nan\n",
|
||
"BtC = nan ± nan\n",
|
||
"P(0,chi²)= 0.00000\n",
|
||
"KdtC = nan ± nan\n",
|
||
"KBdtC = nan ± nan\n",
|
||
"\n",
|
||
"RISULTATI REGRESSIONE York:\n",
|
||
"AtY = nan ± inf\n",
|
||
"BtY = nan ± nan\n",
|
||
"P(0,chi²)= 0.00000\n",
|
||
"KdtY = nan ± nan\n",
|
||
"KBdtY = nan ± nan\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(\"RISULTATI senza ERRORE STRUMENTALE (cronometro):\")\n",
|
||
"print(f\"Media pesata K = {KdtM:.5f} ± {uKdtM:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE OLS:\")\n",
|
||
"print(f\"Atols = {Atols:.5f} ± {uAtols:.5f}\")\n",
|
||
"print(f\"Btols = {Btols:.5f} ± {uBtols:.5f}\")\n",
|
||
"print(f\"P(0,chi²)= {Ptols:.5f}\")\n",
|
||
"print(f\"Kdtols = {Kdtols:.5f} ± {uKdtols:.5f}\")\n",
|
||
"print(f\"KBdtols = {KBdtols:.5f} ± {uKBdtols:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE Carpi:\")\n",
|
||
"print(f\"AtC = {AtC:.5f} ± {uAtC:.5f}\")\n",
|
||
"print(f\"BtC = {BtC:.5f} ± {uBtC:.5f}\")\n",
|
||
"print(f\"P(0,chi²)= {PtC:.5f}\")\n",
|
||
"print(f\"KdtC = {KdtC:.5f} ± {uKdtC:.5f}\")\n",
|
||
"print(f\"KBdtC = {KBdtC:.5f} ± {uKBdtC:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI REGRESSIONE York:\")\n",
|
||
"print(f\"AtY = {AtY:.5f} ± {uAtY:.5f}\")\n",
|
||
"print(f\"BtY = {BtY:.5f} ± {uBtY:.5f}\")\n",
|
||
"print(f\"P(0,chi²)= {PtY:.5f}\")\n",
|
||
"print(f\"KdtY = {KdtY:.5f} ± {uKdtY:.5f}\")\n",
|
||
"print(f\"KBdtY = {KBdtY:.5f} ± {uKBdtY:.5f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "70201336",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Aggiungi gli errori strumentali"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 50,
|
||
"id": "dfcd391e",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"res_t = 0.000500\n",
|
||
"res_t2 = nan\n",
|
||
"res_uAdt = nan\n",
|
||
"uKdt_strum = nan\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"res_t = 0.01 / 20 # risoluzione cronometro\n",
|
||
"res_t2 = np.max(2 * df.t * res_t)\n",
|
||
"\n",
|
||
"res_uAdt = np.max(np.sqrt( (1 / Meq)**2* res_t2**2 +(T2t / Meq**2)**2 * res_b**2))\n",
|
||
"uKdt_strum = np.max(np.abs(4 * np.pi**2 / Adt**2) * res_uAdt) / 1000\n",
|
||
"\n",
|
||
"print(f\"res_t = {res_t:.6f}\")\n",
|
||
"print(f\"res_t2 = {res_t2:.6f}\")\n",
|
||
"print(f\"res_uAdt = {res_uAdt:.6f}\")\n",
|
||
"print(f\"uKdt_strum = {uKdt_strum:.6f}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 51,
|
||
"id": "b52fea3d",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"uKdtM_fin = np.sqrt(uKdtM**2 + uKdt_strum**2)\n",
|
||
"\n",
|
||
"uAtols_fin = np.sqrt(uAtols**2 + res_uAdt**2)\n",
|
||
"uBtols_fin = np.sqrt(uBtols**2 + res_uAdt**2)\n",
|
||
"uKdtols_fin = np.sqrt(uKdtols**2 + uKdt_strum**2)\n",
|
||
"\n",
|
||
"uAtC_fin = np.sqrt(uAtC**2 + res_uAdt**2)\n",
|
||
"uBtC_fin = np.sqrt(uBtC**2 + res_uAdt**2)\n",
|
||
"uKdtC_fin = np.sqrt(uKdtC**2 + uKdt_strum**2)\n",
|
||
"\n",
|
||
"uAtY_fin = np.sqrt(uAtY**2 + res_uAdt**2)\n",
|
||
"uBtY_fin = np.sqrt(uBtY**2 + res_uAdt**2)\n",
|
||
"uKdtY_fin = np.sqrt(uKdtY**2 + uKdt_strum**2)\n",
|
||
"\n",
|
||
"uy_fin_t = np.sqrt(datat[\"uy\"]**2 + res_t2**2)\n",
|
||
"ux_fin_t = np.sqrt(datat[\"ux\"]**2 + res_b**2)\n",
|
||
"\n",
|
||
"GdLt = len(datat) - 2\n",
|
||
"\n",
|
||
"F_fit_tols = Btols + Atols * datat[\"x\"]\n",
|
||
"sigma_tols = np.sqrt(uy_fin_t**2 + (Atols * ux_fin_t)**2)\n",
|
||
"chi2_tols = np.sum(((datat[\"y\"] - F_fit_tols) / sigma_tols)**2)\n",
|
||
"\n",
|
||
"F_fit_tC = BtC + AtC * datat[\"x\"]\n",
|
||
"sigma_tC = np.sqrt(uy_fin_t**2 + (AtC * ux_fin_t)**2)\n",
|
||
"chi2_tC = np.sum(((datat[\"y\"] - F_fit_tC) / sigma_tC)**2)\n",
|
||
"\n",
|
||
"F_fit_tY = BtY + AtY * datat[\"x\"]\n",
|
||
"sigma_tY = np.sqrt(uy_fin_t**2 + (AtY * ux_fin_t)**2)\n",
|
||
"chi2_tY = np.sum(((datat[\"y\"] - F_fit_tY) / sigma_tY)**2)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "858bbff7",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Risultati della propagazione dell'errore"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 52,
|
||
"id": "0b1e4a1d",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"RISULTATI CON ERRORE STRUMENTALE (cronometro):\n",
|
||
"Media pesata K = nan ± nan\n",
|
||
"\n",
|
||
"RISULTATI OLS:\n",
|
||
"Atols = nan ± nan\n",
|
||
"Btols = nan ± nan\n",
|
||
"Kdtols = nan ± nan\n",
|
||
"Chi² = 0.00000 | rid = 0.00000 | P = 0.00000\n",
|
||
"\n",
|
||
"RISULTATI Carpi:\n",
|
||
"AtC = nan ± nan\n",
|
||
"BtC = nan ± nan\n",
|
||
"KdtC = nan ± nan\n",
|
||
"Chi² = 0.00000 | rid = 0.00000 | P = 0.00000\n",
|
||
"\n",
|
||
"RISULTATI York:\n",
|
||
"AtY = nan ± nan\n",
|
||
"BtY = nan ± nan\n",
|
||
"KdtY = nan ± nan\n",
|
||
"Chi² = 0.00000 | rid = 0.00000 | P = 0.00000\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"print(\"RISULTATI CON ERRORE STRUMENTALE (cronometro):\")\n",
|
||
"print(f\"Media pesata K = {KdtM:.5f} ± {uKdtM_fin:.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI OLS:\")\n",
|
||
"print(f\"Atols = {Atols:.5f} ± {uAtols_fin:.5f}\")\n",
|
||
"print(f\"Btols = {Btols:.5f} ± {uBtols_fin:.5f}\")\n",
|
||
"print(f\"Kdtols = {Kdtols:.5f} ± {uKdtols_fin:.5f}\")\n",
|
||
"print(f\"Chi² = {chi2_tols:.5f} | rid = {chi2_tols/GdLt:.5f} | P = {chi2.cdf(chi2_tols, GdLt):.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI Carpi:\")\n",
|
||
"print(f\"AtC = {AtC:.5f} ± {uAtC_fin:.5f}\")\n",
|
||
"print(f\"BtC = {BtC:.5f} ± {uBtC_fin:.5f}\")\n",
|
||
"print(f\"KdtC = {KdtC:.5f} ± {uKdtC_fin:.5f}\")\n",
|
||
"print(f\"Chi² = {chi2_tC:.5f} | rid = {chi2_tC/GdLt:.5f} | P = {chi2.cdf(chi2_tC, GdLt):.5f}\")\n",
|
||
"\n",
|
||
"print(\"\\nRISULTATI York:\")\n",
|
||
"print(f\"AtY = {AtY:.5f} ± {uAtY_fin:.5f}\")\n",
|
||
"print(f\"BtY = {BtY:.5f} ± {uBtY_fin:.5f}\")\n",
|
||
"print(f\"KdtY = {KdtY:.5f} ± {uKdtY_fin:.5f}\")\n",
|
||
"print(f\"Chi² = {chi2_tY:.5f} | rid = {chi2_tY/GdLt:.5f} | P = {chi2.cdf(chi2_tY, GdLt):.5f}\")"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": ".venv",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.13.5"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|