Skip to content

Latest commit

 

History

History
268 lines (243 loc) · 18.4 KB

nd.md

File metadata and controls

268 lines (243 loc) · 18.4 KB

Normal Distribution কি

যখন আমরা কোন রিয়েল লাইফ ডাটা কালেকশনকে রিপ্রেসেন্ট/ডিস্ট্রিবিউট (স্প্রেড আউট) করি তখন সেটার চেহারা বিভিন্ন রকম হতে পারে। যেমন নিচের ডাটাসেটের হিস্টোগ্রাম শো করলে দেখা যাচ্ছে বাম দিকে লম্বা বার বেশি,

x = np.array([20, 30, 30, 30, 20, 20, 50, 20, 20, 30, 40, 40, 40,  50, 60, 60, 90])

plt.hist(x, 15)
plt.show()

![](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAW4AAAD8CAYAAABXe05zAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz AAALEgAACxIB0t1+/AAADLVJREFUeJzt3GGMZXV9xvHv012qgkQERkJZpkOjwRBSQCeIgRpdq11d gkljE0hrfGE7bzSFxsSsadqEdzRprH3RNNmIbdMqtlVoza4iVDHWpoXuwmJ3WahUtwpBV9pStE1s wV9f3LM6nc7s3IW5M+dHv5/kZu459z8nT07OPHPu/55zU1VIkvr4sa0OIEk6NRa3JDVjcUtSMxa3 JDVjcUtSMxa3JDVjcUtSMxa3JDVjcUtSM9tnsdFzzz23FhYWZrFpSXpBOnjw4JNVNTfN2JkU98LC AgcOHJjFpiXpBSnJP0871qkSSWrG4pakZixuSWrG4pakZixuSWpmqqtKkhwDvgs8CzxTVYuzDCVJ WtupXA74pqp6cmZJJElTcapEkpqZtrgLuCvJwSRLswwkSTq5aadKrqmqx5O8Arg7ycNV9aXlA4ZC XwKYn59/zoEW9ux/zr+7mmO37N7Q7UnSVpvqjLuqHh9+HgfuAK5cZczeqlqsqsW5ualut5ckPQfr FneSM5KceeI58Fbg8KyDSZJWN81UyXnAHUlOjP94Vd0501SSpDWtW9xV9TXgsk3IIkmagpcDSlIz FrckNWNxS1IzFrckNWNxS1IzFrckNWNxS1IzFrckNWNxS1IzFrckNWNxS1IzFrckNWNxS1IzFrck NWNxS1IzFrckNWNxS1IzFrckNWNxS1IzFrckNWNxS1IzFrckNWNxS1IzFrckNWNxS1IzFrckNWNx S1IzFrckNWNxS1IzFrckNWNxS1IzFrckNTN1cSfZluSBJPtmGUiSdHKncsZ9I3B0VkEkSdOZqriT 7AB2Ax+ZbRxJ0nqmPeP+MPAB4AczzCJJmsL29QYkuRY4XlUHk7zxJOOWgCWA+fn5DQs4Ngt79m/4 No/dsnvDtynphWuaM+6rgeuSHAM+AexM8icrB1XV3qparKrFubm5DY4pSTph3eKuqg9W1Y6qWgCu B75QVb8082SSpFV5HbckNbPuHPdyVfVF4IszSSJJmopn3JLUjMUtSc1Y3JLUjMUtSc1Y3JLUjMUt Sc1Y3JLUjMUtSc1Y3JLUjMUtSc1Y3JLUjMUtSc1Y3JLUjMUtSc1Y3JLUjMUtSc1Y3JLUjMUtSc1Y 3JLUjMUtSc1Y3JLUjMUtSc1Y3JLUjMUtSc1Y3JLUjMUtSc1Y3JLUjMUtSc1Y3JLUjMUtSc1Y3JLU jMUtSc1Y3JLUzLrFneTFSe5L8mCSI0lu3oxgkqTVbZ9izPeBnVX1vSSnAV9O8tmq+rsZZ5MkrWLd 4q6qAr43LJ42PGqWoSRJa5tqjjvJtiSHgOPA3VV172xjSZLWMs1UCVX1LHB5krOAO5JcWlWHl49J sgQsAczPz294UE1vYc/+Dd3esVt2b+j2JD0/p3RVSVU9BdwD7Frltb1VtVhVi3NzcxuVT5K0wjRX lcwNZ9okeQnwFuDhWQeTJK1umqmS84E/SrKNSdH/WVXtm20sSdJaprmq5CvAFZuQRZI0Be+clKRm LG5JasbilqRmLG5JasbilqRmLG5JasbilqRmLG5JasbilqRmLG5JasbilqRmLG5JasbilqRmLG5J asbilqRmLG5JasbilqRmLG5JasbilqRmLG5JasbilqRmLG5JasbilqRmLG5JasbilqRmLG5Jasbi lqRmLG5JasbilqRmLG5JasbilqRmLG5Jambd4k5yYZJ7kjyU5EiSGzcjmCRpddunGPMM8P6quj/J mcDBJHdX1UMzziZJWsW6Z9xV9URV3T88/y5wFLhg1sEkSas7pTnuJAvAFcC9swgjSVrfNFMlACR5 KfAp4KaqenqV15eAJYD5+fkNC6gXpoU9+zd0e8du2b2h2xt7Pv3/NtUZd5LTmJT2x6rq9tXGVNXe qlqsqsW5ubmNzChJWmaaq0oC3AocraoPzT6SJOlkpjnjvhp4F7AzyaHh8fYZ55IkrWHdOe6q+jKQ TcgiSZqCd05KUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMW tyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1 Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjMWtyQ1Y3FLUjPrFneSjyY5nuTwZgSSJJ3c NGfcfwjsmnEOSdKU1i3uqvoS8K+bkEWSNIXtG7WhJEvAEsD8/PxGbVaSZmZhz/4N3d6xW3Zv6PbW smEfTlbV3qparKrFubm5jdqsJGkFryqRpGYsbklqZprLAW8D/ha4OMljSd4z+1iSpLWs++FkVd2w GUEkSdNxqkSSmrG4JakZi1uSmrG4JakZi1uSmrG4JakZi1uSmrG4JakZi1uSmrG4JakZi1uSmrG4 JakZi1uSmrG4JakZi1uSmrG4JakZi1uSmrG4JakZi1uSmrG4JakZi1uSmrG4JakZi1uSmrG4JakZ i1uSmrG4JakZi1uSmrG4JakZi1uSmrG4JakZi1uSmrG4JamZqYo7ya4kjyR5NMmeWYeSJK1t3eJO sg34PeBtwCXADUkumXUwSdLqpjnjvhJ4tKq+VlX/BXwCeMdsY0mS1jJNcV8AfHPZ8mPDOknSFkhV nXxA8k5gV1X98rD8LuB1VfW+FeOWgKVh8WLgkeeY6Vzgyef4u5utU1bolbdTVuiVt1NW6JX3+WT9 yaqam2bg9inGPA5cuGx5x7Duf6mqvcDeqeKdRJIDVbX4fLezGTplhV55O2WFXnk7ZYVeeTcr6zRT JX8PvCrJRUl+HLge+PRsY0mS1rLuGXdVPZPkfcDngG3AR6vqyMyTSZJWNc1UCVX1GeAzM85ywvOe btlEnbJCr7ydskKvvJ2yQq+8m5J13Q8nJUnj4i3vktTMlhV3kguT3JPkoSRHktw4rD87yd1Jvjr8 fPlWZVwuyYuT3JfkwSHvzcP6i5LcO3wdwJ8OH+COQpJtSR5Ism9YHnPWY0n+IcmhJAeGdWM9Fs5K 8skkDyc5muT1I8568bBPTzyeTnLTiPP+2vD3dTjJbcPf3SiP2yQ3DjmPJLlpWLcp+3Urz7ifAd5f VZcAVwHvHW6l3wN8vqpeBXx+WB6D7wM7q+oy4HJgV5KrgN8CfqeqXgn8G/CeLcy40o3A0WXLY84K 8KaqunzZ5VRjPRZ+F7izql4NXMZkH48ya1U9MuzTy4HXAv8J3MEI8ya5APhVYLGqLmVyMcT1jPC4 TXIp8CtM7iy/DLg2ySvZrP1aVaN4AH8JvIXJjTvnD+vOBx7Z6myrZD0duB94HZOL7bcP618PfG6r 8w1ZdgwHzk5gH5CxZh3yHAPOXbFudMcC8DLg6wyfD4056yrZ3wr8zVjz8qO7tM9mcuHEPuDnxnjc Ar8A3Lps+TeAD2zWfh3FHHeSBeAK4F7gvKp6YnjpW8B5WxTr/ximHg4Bx4G7gX8CnqqqZ4YhY/o6 gA8zOZB+MCyfw3izAhRwV5KDw124MM5j4SLgO8AfDNNQH0lyBuPMutL1wG3D89HlrarHgd8GvgE8 Afw7cJBxHreHgZ9Jck6S04G3M7lRcVP265YXd5KXAp8Cbqqqp5e/VpN/W6O57KWqnq3JW84dTN4i vXqLI60qybXA8ao6uNVZTsE1VfUaJt9C+d4kb1j+4oiOhe3Aa4Dfr6orgP9gxdvhEWX9oWFe+Drg z1e+Npa8w3zwO5j8c/wJ4Axg15aGWkNVHWUyhXMXcCdwCHh2xZiZ7dctLe4kpzEp7Y9V1e3D6m8n OX94/XwmZ7ejUlVPAfcwedt2VpIT18Ov+nUAW+Bq4Lokx5h8m+NOJvOyY8wK/PBsi6o6zmQO9krG eSw8BjxWVfcOy59kUuRjzLrc24D7q+rbw/IY8/4s8PWq+k5V/TdwO5NjeZTHbVXdWlWvrao3MJl7 /0c2ab9u5VUlAW4FjlbVh5a99Gng3cPzdzOZ+95ySeaSnDU8fwmT+fijTAr8ncOwUeStqg9W1Y6q WmDy9vgLVfWLjDArQJIzkpx54jmTudjDjPBYqKpvAd9McvGw6s3AQ4ww6wo38KNpEhhn3m8AVyU5 feiHE/t2rMftK4af88DPAx9ns/brFk7uX8PkbcRXmLzNOMRknugcJh+qfRX4K+Dsrcq4Iu9PAw8M eQ8Dvzms/yngPuBRJm9DX7TVWVfkfiOwb8xZh1wPDo8jwK8P68d6LFwOHBiOhb8AXj7WrEPeM4B/ AV62bN0o8wI3Aw8Pf2N/DLxoxMftXzP5x/Ig8ObN3K/eOSlJzWz5h5OSpFNjcUtSMxa3JDVjcUtS Mxa3JDVjcUtSMxa3JDVjcUtSM/8Dikg1VWc8lD4AAAAASUVORK5CYII= )

অথবা কিছু ডাটার হিস্টোগ্রাম বার গুলো হতে পারে নিচের মত অগোছালো,

x = np.array([40, 30, 80, 30, 20, 80, 50, 20, 20, 60, 40, 40, 40,  50, 60, 60, 90, 80, 70])

plt.hist(x, 15)
plt.show()

![](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAXcAAAD8CAYAAACMwORRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz AAALEgAACxIB0t1+/AAAEd1JREFUeJzt3X+MZXV9xvH347Liz4iyU93u7jg2EI0SAZ0gRmso1HYV AknFBNOqGO0mRiI0JgZsioG/NGnUWo1mI7ZIrWLR2hXwB1WM2sTVWVyQZaWuSmUJygICUhW7+ukf 96DT21numZk7O3e+vl/JzZ4f3zn3yc3ZZ86ce869qSokSW151GoHkCSNn+UuSQ2y3CWpQZa7JDXI cpekBlnuktQgy12SGmS5S1KDLHdJatARq/XEGzZsqJmZmdV6eklak3bt2nV3VU2NGrdq5T4zM8Pc 3NxqPb0krUlJ/qvPOE/LSFKDLHdJapDlLkkNstwlqUGWuyQ1qHe5J1mX5FtJrl5g3ZFJrkyyL8nO JDPjDClJWpzFHLmfD+w9xLrXAz+pqmOAdwPvXG4wSdLS9Sr3JJuB04EPHWLIWcDl3fRVwGlJsvx4 kqSl6Hvk/h7grcCvD7F+E3A7QFUdBO4Hjl52OknSkoy8QzXJGcBdVbUrySnLebIk24BtANPT08vZ lMZg5sJrxrq9295x+li3J2np+hy5vwg4M8ltwMeBU5P809CYO4AtAEmOAJ4E3DO8oaraXlWzVTU7 NTXyoxEkSUs0styr6qKq2lxVM8A5wJeq6i+Ghu0AXttNn92NqbEmlST1tuQPDktyKTBXVTuAy4Ar kuwD7mXwS0CStEoWVe5V9WXgy930xfOW/wJ45TiDSZKWzjtUJalBlrskNchyl6QGWe6S1CDLXZIa ZLlLUoMsd0lqkOUuSQ2y3CWpQZa7JDXIcpekBlnuktQgy12SGmS5S1KDLHdJapDlLkkNstwlqUEj yz3JY5J8I8mNSfYkuWSBMecmOZBkd/d4w8rElST10edr9h4CTq2qB5OsB76W5LNV9fWhcVdW1Xnj jyhJWqyR5V5VBTzYza7vHrWSoSRJy9PrnHuSdUl2A3cB11XVzgWGvSLJTUmuSrJlrCklSYvSq9yr 6ldVdQKwGTgpyXFDQz4DzFTVc4HrgMsX2k6SbUnmkswdOHBgObklSY9gUVfLVNV9wPXA1qHl91TV Q93sh4DnH+Lnt1fVbFXNTk1NLSWvJKmHPlfLTCU5qpt+LPBS4DtDYzbOmz0T2DvOkJKkxelztcxG 4PIk6xj8MvhEVV2d5FJgrqp2AG9OciZwELgXOHelAkuSRutztcxNwIkLLL943vRFwEXjjSZJWirv UJWkBlnuktQgy12SGmS5S1KDLHdJapDlLkkNstwlqUGWuyQ1yHKXpAZZ7pLUIMtdkhpkuUtSgyx3 SWqQ5S5JDbLcJalBlrskNchyl6QG9fkO1cck+UaSG5PsSXLJAmOOTHJlkn1JdiaZWYmwkqR++hy5 PwScWlXHAycAW5OcPDTm9cBPquoY4N3AO8cbU5K0GCPLvQYe7GbXd48aGnYWcHk3fRVwWpKMLaUk aVFGfkE2QJJ1wC7gGOD9VbVzaMgm4HaAqjqY5H7gaODuoe1sA7YBTE9PLzn0zIXXLPlnD+W2d5w+ 9m2qfePeF38X90Nfw5XR6w3VqvpVVZ0AbAZOSnLcUp6sqrZX1WxVzU5NTS1lE5KkHhZ1tUxV3Qdc D2wdWnUHsAUgyRHAk4B7xhFQkrR4fa6WmUpyVDf9WOClwHeGhu0AXttNnw18qaqGz8tLkg6TPufc NwKXd+fdHwV8oqquTnIpMFdVO4DLgCuS7APuBc5ZscSSpJFGlntV3QScuMDyi+dN/wJ45XijSZKW yjtUJalBlrskNchyl6QGWe6S1CDLXZIaZLlLUoMsd0lqkOUuSQ2y3CWpQZa7JDXIcpekBlnuktQg y12SGmS5S1KDLHdJapDlLkkNstwlqUF9vkN1S5Lrk9ySZE+S8xcYc0qS+5Ps7h4XL7QtSdLh0ec7 VA8Cb6mqG5I8EdiV5LqqumVo3Fer6ozxR5QkLdbII/equrOqbuimfwrsBTatdDBJ0tIt6px7khkG X5a9c4HVL0xyY5LPJnnOIX5+W5K5JHMHDhxYdFhJUj+9yz3JE4BPAhdU1QNDq28Anl5VxwN/D3x6 oW1U1faqmq2q2ampqaVmliSN0Kvck6xnUOwfrapPDa+vqgeq6sFu+lpgfZINY00qSeqtz9UyAS4D 9lbVuw4x5mndOJKc1G33nnEGlST11+dqmRcBrwa+nWR3t+xtwDRAVX0QOBt4Y5KDwM+Bc6qqViCv JKmHkeVeVV8DMmLM+4D3jSuUJGl5vENVkhpkuUtSgyx3SWqQ5S5JDbLcJalBlrskNchyl6QGWe6S 1CDLXZIaZLlLUoMsd0lqkOUuSQ2y3CWpQZa7JDXIcpekBlnuktQgy12SGtTnO1S3JLk+yS1J9iQ5 f4ExSfLeJPuS3JTkeSsTV5LUR5/vUD0IvKWqbkjyRGBXkuuq6pZ5Y14GHNs9XgB8oPtXkrQKRh65 V9WdVXVDN/1TYC+waWjYWcBHauDrwFFJNo49rSSplz5H7r+RZAY4Edg5tGoTcPu8+f3dsjuHfn4b sA1genp6cUnXmJkLrxnr9m57x+lj3d5a4GsoLV3vN1STPAH4JHBBVT2wlCerqu1VNVtVs1NTU0vZ hCSph17lnmQ9g2L/aFV9aoEhdwBb5s1v7pZJklZBn6tlAlwG7K2qdx1i2A7gNd1VMycD91fVnYcY K0laYX3Oub8IeDXw7SS7u2VvA6YBquqDwLXAy4F9wM+A140/qiSpr5HlXlVfAzJiTAFvGlcoSdLy eIeqJDXIcpekBlnuktQgy12SGmS5S1KDLHdJapDlLkkNstwlqUGWuyQ1yHKXpAZZ7pLUIMtdkhpk uUtSgyx3SWqQ5S5JDbLcJalBfb5m78NJ7kpy8yHWn5Lk/iS7u8fF448pSVqMPl+z94/A+4CPPMKY r1bVGWNJJElatpFH7lX1FeDew5BFkjQm4zrn/sIkNyb5bJLnjGmbkqQl6nNaZpQbgKdX1YNJXg58 Gjh2oYFJtgHbAKanp8fw1JKkhSz7yL2qHqiqB7vpa4H1STYcYuz2qpqtqtmpqanlPrUk6RCWXe5J npYk3fRJ3TbvWe52JUlLN/K0TJKPAacAG5LsB94OrAeoqg8CZwNvTHIQ+DlwTlXViiWWJI00styr 6lUj1r+PwaWSkqQJ4R2qktQgy12SGmS5S1KDLHdJapDlLkkNstwlqUGWuyQ1yHKXpAZZ7pLUIMtd khpkuUtSgyx3SWqQ5S5JDbLcJalBlrskNchyl6QGWe6S1KCR5Z7kw0nuSnLzIdYnyXuT7EtyU5Ln jT+mJGkx+hy5/yOw9RHWvww4tntsAz6w/FiSpOUYWe5V9RXg3kcYchbwkRr4OnBUko3jCihJWrxx nHPfBNw+b35/t0yStEqOOJxPlmQbg1M3TE9PH86nln4nzVx4zdi3eds7Th/7NifZWn0Nx3Hkfgew Zd785m7Z/1NV26tqtqpmp6amxvDUkqSFjKPcdwCv6a6aORm4v6ruHMN2JUlLNPK0TJKPAacAG5Ls B94OrAeoqg8C1wIvB/YBPwNet1JhJUn9jCz3qnrViPUFvGlsiSRJy+YdqpLUIMtdkhpkuUtSgyx3 SWqQ5S5JDbLcJalBlrskNchyl6QGWe6S1CDLXZIaZLlLUoMsd0lqkOUuSQ2y3CWpQZa7JDXIcpek BlnuktSgXuWeZGuSW5PsS3LhAuvPTXIgye7u8YbxR5Uk9dXnO1TXAe8HXgrsB76ZZEdV3TI09Mqq Om8FMkqSFqnPkftJwL6q+n5V/RL4OHDWysaSJC1Hn3LfBNw+b35/t2zYK5LclOSqJFvGkk6StCTj ekP1M8BMVT0XuA64fKFBSbYlmUsyd+DAgTE9tSRpWJ9yvwOYfyS+uVv2G1V1T1U91M1+CHj+Qhuq qu1VNVtVs1NTU0vJK0nqoU+5fxM4NskzkjwaOAfYMX9Ako3zZs8E9o4voiRpsUZeLVNVB5OcB3we WAd8uKr2JLkUmKuqHcCbk5wJHATuBc5dwcySpBFGljtAVV0LXDu07OJ50xcBF403miRpqbxDVZIa ZLlLUoMsd0lqkOUuSQ2y3CWpQZa7JDXIcpekBlnuktQgy12SGmS5S1KDLHdJapDlLkkNstwlqUGW uyQ1yHKXpAZZ7pLUIMtdkhrUq9yTbE1ya5J9SS5cYP2RSa7s1u9MMjPuoJKk/kaWe5J1wPuBlwHP Bl6V5NlDw14P/KSqjgHeDbxz3EElSf31OXI/CdhXVd+vql8CHwfOGhpzFnB5N30VcFqSjC+mJGkx +pT7JuD2efP7u2ULjqmqg8D9wNHjCChJWrxU1SMPSM4GtlbVG7r5VwMvqKrz5o25uRuzv5v/Xjfm 7qFtbQO2dbPPBG5dYu4NwN0jR02OtZR3LWWFtZV3LWWFtZV3LWWF5eV9elVNjRp0RI8N3QFsmTe/ uVu20Jj9SY4AngTcM7yhqtoObO/xnI8oyVxVzS53O4fLWsq7lrLC2sq7lrLC2sq7lrLC4cnb57TM N4FjkzwjyaOBc4AdQ2N2AK/tps8GvlSj/iSQJK2YkUfuVXUwyXnA54F1wIerak+SS4G5qtoBXAZc kWQfcC+DXwCSpFXS57QMVXUtcO3QsovnTf8CeOV4oz2iZZ/aOczWUt61lBXWVt61lBXWVt61lBUO Q96Rb6hKktYeP35Akho08eWeZEuS65PckmRPkvO75U9Jcl2S73b/PnkCsj4myTeS3NhlvaRb/ozu Yxn2dR/T8OjVzjpfknVJvpXk6m5+IvMmuS3Jt5PsTjLXLZu4/eBhSY5KclWS7yTZm+SFk5g3yTO7 1/ThxwNJLpjErA9L8lfd/7Gbk3ys+783qfvt+V3OPUku6Jat+Gs78eUOHATeUlXPBk4G3tR9/MGF wBer6ljgi938ansIOLWqjgdOALYmOZnBxzG8u/t4hp8w+LiGSXI+sHfe/CTn/aOqOmHeZWSTuB88 7O+Az1XVs4DjGbzGE5e3qm7tXtMTgOcDPwP+lQnMCpBkE/BmYLaqjmNwocc5TOB+m+Q44C8Z3Ol/ PHBGkmM4HK9tVa2pB/BvwEsZ3AC1sVu2Ebh1tbMN5XwccAPwAgY3KxzRLX8h8PnVzjcv5+Zu5zoV uBrIpOYFbgM2DC2byP2Awb0eP6B7X2vS887L9yfAf0xyVn57R/xTGFwUcjXwp5O43zK40OSyefN/ A7z1cLy2a+HI/Te6T5s8EdgJPLWq7uxW/Qh46irF+j+6Uxy7gbuA64DvAffV4GMZYOGPb1hN72Gw s/26mz+ayc1bwBeS7OrudoYJ3Q+AZwAHgH/oTnl9KMnjmdy8DzsH+Fg3PZFZq+oO4G+BHwJ3Mvi4 k11M5n57M/CHSY5O8jjg5Qxu+Fzx13bNlHuSJwCfBC6oqgfmr6vBr7+JuOynqn5Vgz9vNzP4U+xZ qxzpkJKcAdxVVbtWO0tPL66q5zH4hNI3JXnJ/JWTtB8wOKJ8HvCBqjoR+G+G/vSesLx056jPBP5l eN0kZe3OT5/F4Bfo7wOPB7auaqhDqKq9DE4XfQH4HLAb+NXQmBV5bddEuSdZz6DYP1pVn+oW/zjJ xm79RgZHyhOjqu4Drmfw5+FR3ccywMIf37BaXgScmeQ2Bp/2eSqD88QTmbc7YqOq7mJwTvgkJnc/ 2A/sr6qd3fxVDMp+UvPC4JfmDVX1425+UrP+MfCDqjpQVf8DfIrBvjyp++1lVfX8qnoJg/cC/pPD 8NpOfLknCYM7YPdW1bvmrZr/kQevZXAuflUlmUpyVDf9WAbvDexlUPJnd8MmIitAVV1UVZuraobB n+Nfqqo/ZwLzJnl8kic+PM3g3PDNTOB+AFBVPwJuT/LMbtFpwC1MaN7Oq/jtKRmY3Kw/BE5O8riu Hx5+bSduvwVI8nvdv9PAnwH/zOF4bVf7DYceb0i8mMGfLDcx+JNmN4PzVkczeCPwu8C/A0+ZgKzP Bb7VZb0ZuLhb/gfAN4B9DP7kPXK1sy6Q/RTg6knN22W6sXvsAf66Wz5x+8G8zCcAc93+8GngyZOa l8GpjXuAJ81bNpFZu2yXAN/p/p9dARw5ifttl/WrDH753AicdrheW+9QlaQGTfxpGUnS4lnuktQg y12SGmS5S1KDLHdJapDlLkkNstwlqUGWuyQ16H8BOtl2YBZhBDIAAAAASUVORK5CYII= )

কিন্তু অনেক সময় বাস্তবের কিছু ডাটাকে (কিছু ছাত্রের উচ্চতার মান, তাদের পরীক্ষায় প্রাপ্ত নম্বর, একটি মেশিন দারা তৈরি কোন প্রোডাক্টের সাইজ, জনগণের আয় ইত্যাদি) ডিস্ট্রিবিউট করলে নিচের মত চেহারা পাওয়া যায়,

sizes = np.array([9, 8, 8, 9, 9, 1, 4, 5, 6, 7, 8, 9, 10, 10, 11, 11, 11, 11, 11, 13, 12, 12, 12, 12, 13, 13, 14, 14, 14, 15, 15, 15, 16, 17, 18, 20])

plt.hist(sizes)
plt.show()

![](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAW4AAAD8CAYAAABXe05zAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz AAALEgAACxIB0t1+/AAADHJJREFUeJzt3W+MZXV5wPHv0x2IBYks7kQRGAdNY4JNWrcTg2IJEUNx 10BtGoPxD2qTiUlpoakx25iqL5famtqmabNFWtsSNSK2xEUFrabxBRt31+XPslj+dFahC6y1YTV9 gdTHF/esuY73zj1k5pyzz/D9JJO5c+/vzn1y5uyXc8/cO0RmIkmq45eGHkCS9NwYbkkqxnBLUjGG W5KKMdySVIzhlqRiDLckFWO4JakYwy1Jxcx18U23bduWi4uLXXxrSdqUDhw48P3MnG+ztpNwLy4u sn///i6+tSRtShFxtO1aT5VIUjGGW5KKMdySVIzhlqRiDLckFWO4JakYwy1JxRhuSSrGcEtSMZ28 c1I6VS3u2jvI467s3jnI42pz8ohbkoox3JJUjOGWpGIMtyQVY7glqRjDLUnFGG5JKsZwS1IxhluS ijHcklSM4ZakYgy3JBVjuCWpGMMtScUYbkkqxnBLUjGGW5KKMdySVEyrcEfEH0XE4Yi4PyI+HREv 6HowSdJkM8MdEecBfwgsZeavAluAa7oeTJI0WdtTJXPAL0fEHHAG8N/djSRJWsvMcGfm48CfA98F jgFPZ+adXQ8mSZqszamSrcDVwIXAy4AzI+KdE9YtR8T+iNh//PjxjZ9UkgS0O1XyJuC/MvN4Zv4Y uA14/epFmbknM5cyc2l+fn6j55QkNdqE+7vAxRFxRkQEcDlwpNuxJEnTtDnHvQ+4FTgI3NfcZ0/H c0mSpphrsygzPwJ8pONZJEkt+M5JSSrGcEtSMYZbkoox3JJUjOGWpGIMtyQVY7glqRjDLUnFGG5J KsZwS1IxhluSijHcklSM4ZakYgy3JBVjuCWpGMMtScUYbkkqxnBLUjGGW5KKMdySVIzhlqRiDLck FWO4JakYwy1JxRhuSSrGcEtSMYZbkoox3JJUjOGWpGIMtyQVY7glqRjDLUnFGG5JKsZwS1IxhluS ijHcklSM4ZakYlqFOyLOjohbI+LBiDgSEa/rejBJ0mRzLdd9AvhyZv5uRJwOnNHhTJKkNcwMd0S8 CLgUeA9AZj4DPNPtWJKkadqcKrkQOA78Q0R8OyJuiogzO55LkjRFZObaCyKWgLuBSzJzX0R8AjiR mX+6at0ysAywsLDwG0ePHu1oZG0Gi7v2Dj3C88bK7p1Dj6AWIuJAZi61WdvmiPsx4LHM3Nd8fSuw ffWizNyTmUuZuTQ/P99+WknSczIz3Jn5BPC9iHhVc9XlwAOdTiVJmqrtq0r+ALileUXJo8B7uxtJ krSWVuHOzENAq3MvkqRu+c5JSSrGcEtSMYZbkoox3JJUjOGWpGIMtyQVY7glqRjDLUnFGG5JKsZw S1IxhluSijHcklSM4ZakYgy3JBVjuCWpGMMtScUYbkkqxnBLUjGGW5KKMdySVIzhlqRiDLckFWO4 JakYwy1JxRhuSSrGcEtSMYZbkoox3JJUjOGWpGIMtyQVY7glqRjDLUnFGG5JKsZwS1IxhluSijHc klSM4ZakYlqHOyK2RMS3I+KLXQ4kSVrbcznivh440tUgkqR2WoU7Is4HdgI3dTuOJGmWtkfcfwl8 EPhJh7NIklqYm7UgIt4CPJWZByLisjXWLQPLAAsLCxs2oLqzuGvv0COoB0P9nFd27xzkcZ8P2hxx XwJcFRErwGeAN0bEv6xelJl7MnMpM5fm5+c3eExJ0kkzw52Zf5KZ52fmInAN8O+Z+c7OJ5MkTeTr uCWpmJnnuMdl5jeAb3QyiSSpFY+4JakYwy1JxRhuSSrGcEtSMYZbkoox3JJUjOGWpGIMtyQVY7gl qRjDLUnFGG5JKsZwS1IxhluSijHcklSM4ZakYgy3JBVjuCWpGMMtScUYbkkqxnBLUjGGW5KKMdyS VIzhlqRiDLckFWO4JakYwy1JxRhuSSrGcEtSMYZbkoox3JJUjOGWpGIMtyQVY7glqRjDLUnFGG5J KsZwS1IxhluSipkZ7oi4ICK+HhEPRMThiLi+j8EkSZPNtVjzLPDHmXkwIs4CDkTEXZn5QMezSZIm mHnEnZnHMvNgc/mHwBHgvK4HkyRN9pzOcUfEIvAaYF8Xw0iSZmtzqgSAiHgh8Hnghsw8MeH2ZWAZ YGFhYcMGfD5Y3LV36BGkDTfkfr2ye+dgj92HVkfcEXEao2jfkpm3TVqTmXsycykzl+bn5zdyRknS mDavKgngk8CRzPx49yNJktbS5oj7EuBdwBsj4lDzsaPjuSRJU8w8x52Z3wSih1kkSS34zklJKsZw S1IxhluSijHcklSM4ZakYgy3JBVjuCWpGMMtScUYbkkqxnBLUjGGW5KKMdySVIzhlqRiDLckFWO4 JakYwy1JxRhuSSrGcEtSMTP/12V9W9y1d+gRJBU3VEdWdu/s5XE84pakYgy3JBVjuCWpGMMtScUY bkkqxnBLUjGGW5KKMdySVIzhlqRiDLckFWO4JakYwy1JxRhuSSrGcEtSMYZbkoox3JJUjOGWpGIM tyQV0yrcEXFlRHwnIh6OiF1dDyVJmm5muCNiC/A3wJuBi4C3R8RFXQ8mSZqszRH3a4GHM/PRzHwG +AxwdbdjSZKmaRPu84DvjX39WHOdJGkAcxv1jSJiGVhuvvxRRHxno773BtsGfH/oIdbgfOvjfOvj fOsQN65rvpe3Xdgm3I8DF4x9fX5z3c/JzD3AnrYPPJSI2J+ZS0PPMY3zrY/zrY/zrU9f87U5VfIt 4Fci4sKIOB24Bri927EkSdPMPOLOzGcj4jrgK8AW4ObMPNz5ZJKkiVqd487MO4A7Op6lL6f66Rzn Wx/nWx/nW59e5ovM7ONxJEkbxLe8S1IxmzLcEXFBRHw9Ih6IiMMRcf2ENZdFxNMRcaj5+HDPM65E xH3NY++fcHtExF81f2bg3ojY3uNsrxrbLoci4kRE3LBqTa/bLyJujoinIuL+sevOiYi7IuKh5vPW Kfe9tlnzUERc2+N8H4uIB5uf3xci4uwp911zX+hwvo9GxONjP8MdU+7b+Z+8mDLfZ8dmW4mIQ1Pu 28f2m9iUwfbBzNx0H8C5wPbm8lnAfwIXrVpzGfDFAWdcAbatcfsO4EtAABcD+waacwvwBPDyIbcf cCmwHbh/7Lo/A3Y1l3cBN0643znAo83nrc3lrT3NdwUw11y+cdJ8bfaFDuf7KPCBFj//R4BXAKcD 96z+t9TVfKtu/wvgwwNuv4lNGWof3JRH3Jl5LDMPNpd/CByh3rs9rwb+KUfuBs6OiHMHmONy4JHM PDrAY/9MZv4H8INVV18NfKq5/Cngtyfc9beAuzLzB5n5v8BdwJV9zJeZd2bms82XdzN6D8Qgpmy/ Nnr5kxdrzRcRAbwN+PRGP25bazRlkH1wU4Z7XEQsAq8B9k24+XURcU9EfCkiXt3rYJDAnRFxoHnX 6Wqnyp8auIbp/2CG3H4AL8nMY83lJ4CXTFhzqmzH9zF6BjXJrH2hS9c1p3JunvI0/1TYfr8JPJmZ D025vdftt6opg+yDmzrcEfFC4PPADZl5YtXNBxk9/f814K+Bf+15vDdk5nZGf3Xx9yPi0p4ff6bm DVdXAZ+bcPPQ2+/n5Og56Sn5EqmI+BDwLHDLlCVD7Qt/C7wS+HXgGKPTEaeit7P20XZv22+tpvS5 D27acEfEaYw28C2Zedvq2zPzRGb+qLl8B3BaRGzra77MfLz5/BTwBUZPSce1+lMDHXszcDAzn1x9 w9Dbr/HkydNHzeenJqwZdDtGxHuAtwDvaP5h/4IW+0InMvPJzPz/zPwJ8PdTHnfo7TcH/A7w2Wlr +tp+U5oyyD64KcPdnBP7JHAkMz8+Zc1Lm3VExGsZbYv/6Wm+MyPirJOXGf0S6/5Vy24H3t28uuRi 4Omxp2R9mXqkM+T2G3M7cPI39NcC/zZhzVeAKyJia3Mq4Irmus5FxJXAB4GrMvP/pqxpsy90Nd/4 70zeOuVxh/6TF28CHszMxybd2Nf2W6Mpw+yDXf4mdqgP4A2MnrLcCxxqPnYA7wfe36y5DjjM6Lfk dwOv73G+VzSPe08zw4ea68fnC0b/A4tHgPuApZ634ZmMQvyisesG236M/gNyDPgxo3OEvwe8GPga 8BDwVeCcZu0ScNPYfd8HPNx8vLfH+R5mdG7z5D74d83alwF3rLUv9DTfPzf71r2MAnTu6vmar3cw ehXFI33O11z/jyf3ubG1Q2y/aU0ZZB/0nZOSVMymPFUiSZuZ4ZakYgy3JBVjuCWpGMMtScUYbkkq xnBLUjGGW5KK+SlHXqmBKPhh0QAAAABJRU5ErkJggg== )

যেটা অনেকটা বেল (ঘণ্টি) কার্ভের মত অর্থাৎ মাঝখানের বার গুলো লম্বা এবং তার দুপাশের বার গুলো ক্রমান্বয়ে ছোট। এরকম কোন ডাটার ডিস্ট্রিবিউশনকে বলা হয় নরমালি ডিস্ট্রিবিউটেড।

সব ডাটা এমনি এমনি এমন চেহারা নাও পেতে পারে। সেক্ষেত্রে ডাটা গুলোর গড় বা মধ্যক বের করে সেটাকে মাঝখানে রেখে ওই মধ্যম মানের চেয়ে ছোট ও বড় মান গুলোকে যথাক্রমে বাম পাশে এবং ডানপাশে রেখে একটি ডিস্ট্রিবিউশন তৈরি করাকে নরমাল ডিস্ট্রিবিউশন বলা হয়। ডাটাকে এভাবে ডিস্ট্রিবিউট করলে পরবর্তীতে অনেক রকম হিসাব, পর্যবেক্ষণ বা সম্ভাব্যতা বের করা সহজ হয়ে যায়।

নরমালি ডিস্ট্রিবিউটেড কোন ডাটাসেটের mean, median এবং mode মোটামুটি একই হয়। নিচে প্রমাণ করে দেখা যেতে পারে,

np.mean(sizes)
11.194444444444445
np.median(sizes)
11.0
stats.mode(sizes)
ModeResult(mode=array([11]), count=array([5]))