# Start writing code here.. import pandas as pd import numpy as np import seaborn as sns import matplotlib.pyplot as plt from scipy import stats

df = pd.read_csv('cars.csv') df

df = df.sample(n=50, replace=True) df

df["price_usd"].mean()

df["price_usd"].std()

df.dtypes

df.describe()

df.head()

df["price_usd"].mean()

mu, sigma = 6350, 627.27 s = np.random.normal(mu, sigma, 1000) count, bins, ignored = plt.hist(s, 20, normed=True) plt.plot(bins, 1/(sigma * np.sqrt(2 * np.pi)) * np.exp( - (bins - mu)**2 / (2 * sigma**2) ), linewidth=3, color='y') plt.show()

mu = 5 std = 10 snd = stats.norm(mu, std) x = np.linspace(-100, 100, 1000) plt.figure(figsize=(7.5,7.5)) plt.plot(x, snd.pdf(x)) plt.xlim(-60, 60) plt.title('Normal Distribution (Mean = 5, STD = 10)', fontsize='15') plt.xlabel('Values of Random Variable X', fontsize='15') plt.ylabel('Probability', fontsize='15') plt.show()

mu, sigma = 6350, 627.2 # mean and standard deviation s = np.random.normal(mu, sigma, 50) abs(mu - np.mean(s)) 0.0 # may vary abs(sigma - np.std(s, ddof=1)) 0.1 # may vary import matplotlib.pyplot as plt count, bins, ignored = plt.hist(s, 30, density=True) plt.plot(bins, 1/(sigma * np.sqrt(2 * np.pi)) * np.exp( - (bins - mu)**2 / (2 * sigma**2) ), linewidth=2, color='r') plt.show()