import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

data_raw = pd.read_csv("https://jonghank.github.io/ase3001/files/falcon9_launch_data_raw.csv")
data_raw

data_raw['LaunchSite'].value_counts()


data_raw['Orbit'].value_counts()

landing_outcomes = data_raw['Outcome'].value_counts()
landing_outcomes

sns.catplot(y="PayloadMass", x="FlightNumber", hue="Class", \
            data=data_raw, aspect = 5)
plt.xlabel("Flight Number",fontsize=20)
plt.ylabel("Pay load Mass (kg)",fontsize=20)
plt.show()

sns.catplot(y='LaunchSite', x='FlightNumber', hue='Class', \
            data=data_raw, aspect=5)
plt.xlabel("Flight Number",fontsize=20)
plt.ylabel("LaunchSite",fontsize=20)
plt.show()

sns.catplot(y='LaunchSite', x='PayloadMass', hue='Class', \
            data=data_raw, aspect=5)
plt.xlabel("Pauload Mass(Kg)",fontsize=20)
plt.ylabel("LaunchSite",fontsize=20)
plt.show()

df_success=data_raw.groupby('Orbit')['Class'].mean()*100
df_success.plot(kind='bar', figsize=(10,6))
plt.xlabel('Orbit')
plt.ylabel('Success Rate')
plt.title('Relationship between Success Rate and Orbit')

plt.show()

sns.catplot(y='Orbit', x='FlightNumber', hue='Class', \
            data=data_raw, aspect=5)
plt.xlabel("Flight Number",fontsize=20)
plt.ylabel("Orbit",fontsize=20)
plt.show()

sns.catplot(y='Orbit', x='PayloadMass', hue='Class', \
            data=data_raw, aspect=5)
plt.xlabel("Pauload Mass(Kg)",fontsize=20)
plt.ylabel("Orbit",fontsize=20)
plt.show()

data_raw['Date'] = data_raw['Date'].astype(str)
year=[]

def Extract_year(df):
    for i in data_raw["Date"]:
        year.append(i.split("-")[0])
    return year

Extract_year(data_raw)
data_raw['Year']=year
fig,ax=plt.subplots()
df_success1=data_raw.groupby('Year')['Class'].mean()*100
df_success1.plot(kind='line', figsize=(10,6))
plt.xlabel('Year')
plt.ylabel('Success Rate')
plt.title('Relationship between Success Rate and Year')
plt.grid()
plt.show()

features = data_raw[['FlightNumber', 'PayloadMass', 'Orbit', \
                     'LaunchSite', 'Flights', 'GridFins', \
                     'Reused', 'Legs', 'LandingPad', 'Block', \
                     'ReusedCount', 'Serial']]
features

data = pd.read_csv("https://jonghank.github.io/ase3001/files/falcon9_dataset.csv")
data

X = data.iloc[:,:-1].to_numpy()
y = data.iloc[:,-1].to_numpy()*2 - 1

N = len(y)
rand_ind = list(range(N))
np.random.seed(3001)
np.random.shuffle(rand_ind)

N_train = int(N*0.8)
X_train = X[rand_ind[:N_train]]
y_train = y[rand_ind[:N_train]]
X_test = X[rand_ind[N_train:]]
y_test = y[rand_ind[N_train:]]

def solve_svm(X, y, lam=1):

  import cvxpy as cp

  w = cp.Variable(X.shape[1])
  b = cp.Variable()

  obj = cp.sum(cp.pos(1-cp.multiply(y,(X@w-b))))
  reg = cp.sum_squares(w)
  problem = cp.Problem(cp.Minimize(obj + lam*reg))
  problem.solve(solver=cp.CLARABEL)

  return w.value, b.value, obj.value, reg.value

# your code here


def solve_logistic_regression(X, y, lam=1):

  import cvxpy as cp

  w = cp.Variable(X.shape[1])
  b = cp.Variable()

  obj = cp.sum(cp.logistic(-cp.multiply(y,(X@w-b))))
  reg = cp.sum_squares(w)
  problem = cp.Problem(cp.Minimize(obj + lam*reg))
  problem.solve(solver=cp.CLARABEL)

  return w.value, b.value, obj.value, reg.value

# your code here