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

train_data=pd.read_excel('/content/Data_Train.xlsx')

train_data.head()

train_data.info()

train_data.isnull().sum()

train_data.dropna(inplace=True)

train_data.isnull().sum()

train_data.dtypes

def change_into_datetime(col): train_data[col]=pd.to_datetime(train_data[col])

train_data.columns

for i in ['Date_of_Journey','Dep_Time', 'Arrival_Time']: change_into_datetime(i)

train_data.dtypes

train_data['Journey_day']=train_data['Date_of_Journey'].dt.day

train_data['Journey_month']=train_data['Date_of_Journey'].dt.month

train_data.head()

## Since we have converted Date_of_Journey column into integers, Now we can drop as it is of no use. train_data.drop('Date_of_Journey', axis=1, inplace=True)

train_data.head()

def extract_hour(df,col): df[col+"_hour"]=df[col].dt.hour

def extract_min(df,col): df[col+"_minute"]=df[col].dt.minute

def drop_column(df,col): df.drop(col,axis=1,inplace=True)

# Departure time is when a plane leaves the gate. # Similar to Date_of_Journey we can extract values from Dep_Time extract_hour(train_data,'Dep_Time')

# Extracting Minutes extract_min(train_data,'Dep_Time')

# Now we can drop Dep_Time as it is of no use drop_column(train_data,'Dep_Time')

train_data.head()

# Arrival time is when the plane pulls up to the gate. # Similar to Date_of_Journey we can extract values from Arrival_Time # Extracting Hours extract_hour(train_data,'Arrival_Time') # Extracting minutes extract_min(train_data,'Arrival_Time') # Now we can drop Arrival_Time as it is of no use drop_column(train_data,'Arrival_Time')

train_data.head()

'2h 50m'.split(' ')

duration=list(train_data['Duration']) for i in range(len(duration)): if len(duration[i].split(' '))==2: pass else: if 'h' in duration[i]: # Check if duration contains only hour duration[i]=duration[i] + ' 0m' # Adds 0 minute else: duration[i]='0h '+ duration[i] # if duration contains only second, Adds 0 hour

train_data['Duration']=duration

train_data.head()

'2h 50m'.split(' ')[1][0:-1]

def hour(x): return x.split(' ')[0][0:-1]

def min(x): return x.split(' ')[1][0:-1]

train_data['Duration_hours']=train_data['Duration'].apply(hour) train_data['Duration_mins']=train_data['Duration'].apply(min)

train_data.head()

train_data.drop('Duration',axis=1,inplace=True)

train_data.head()

train_data.dtypes

train_data['Duration_hours']=train_data['Duration_hours'].astype(int) train_data['Duration_mins']=train_data['Duration_mins'].astype(int)

train_data.dtypes

train_data.head()

train_data.dtypes

cat_col=[col for col in train_data.columns if train_data[col].dtype=='O'] cat_col

cont_col=[col for col in train_data.columns if train_data[col].dtype!='O'] cont_col

categorical=train_data[cat_col] categorical.head()

categorical['Airline'].value_counts()

plt.figure(figsize=(15,5)) sns.boxplot(y='Price',x='Airline',data=train_data.sort_values('Price',ascending=False))

plt.figure(figsize=(15,5)) sns.boxplot(y='Price',x='Total_Stops',data=train_data.sort_values('Price',ascending=False))

len(categorical['Airline'].unique())

# As Airline is Nominal Categorical data we will perform OneHotEncoding Airline=pd.get_dummies(categorical['Airline'], drop_first=True) Airline.head()

categorical['Source'].value_counts()

# Source vs Price plt.figure(figsize=(15,5)) sns.catplot(y='Price',x='Source',data=train_data.sort_values('Price',ascending=False),kind='boxen')

# As Source is Nominal Categorical data we will perform OneHotEncoding Source=pd.get_dummies(categorical['Source'], drop_first=True) Source.head()

categorical['Destination'].value_counts()

# As Destination is Nominal Categorical data we will perform OneHotEncoding Destination=pd.get_dummies(categorical['Destination'], drop_first=True) Destination.head()

categorical['Route']

categorical['Route_1']=categorical['Route'].str.split('→').str[0] categorical['Route_2']=categorical['Route'].str.split('→').str[1] categorical['Route_3']=categorical['Route'].str.split('→').str[2] categorical['Route_4']=categorical['Route'].str.split('→').str[3] categorical['Route_5']=categorical['Route'].str.split('→').str[4]

categorical.head()

import warnings from warnings import filterwarnings filterwarnings('ignore')

categorical['Route_1'].fillna('None',inplace=True) categorical['Route_2'].fillna('None',inplace=True) categorical['Route_3'].fillna('None',inplace=True) categorical['Route_4'].fillna('None',inplace=True) categorical['Route_5'].fillna('None',inplace=True)

categorical.head()

#now extract how many categories in each cat_feature for feature in categorical.columns: print('{} has total {} categories \n'.format(feature,len(categorical[feature].value_counts())))

# As we will see we have lots of features in Route # One hot encoding will not be a better option lets appply Label Encoding

from sklearn.preprocessing import LabelEncoder encoder=LabelEncoder()

categorical.columns

for i in ['Route_1', 'Route_2', 'Route_3', 'Route_4','Route_5']: categorical[i]=encoder.fit_transform(categorical[i])

categorical.head()

# Additional_Info contains almost 80% no_info,so we can drop this column # We can drop Route as well as we have pre-process that column drop_column(categorical,'Route') drop_column(categorical,'Additional_Info')

categorical.head()

categorical['Total_Stops'].value_counts()

categorical['Total_Stops'].unique()

# As this is case of Ordinal Categorical type we perform LabelEncoder # Here Values are assigned with corresponding key dict={'non-stop':0, '2 stops':2, '1 stop':1, '3 stops':3, '4 stops':4}

categorical['Total_Stops']=categorical['Total_Stops'].map(dict)

categorical.head()

train_data[cont_col]

# Concatenate dataframe --> categorical + Airline + Source + Destination data_train=pd.concat([categorical,Airline,Source,Destination,train_data[cont_col]],axis=1) data_train.head()

drop_column(data_train,'Airline') drop_column(data_train,'Source') drop_column(data_train,'Destination')

data_train.head()

pd.set_option('display.max_columns',35)

data_train.head()

data_train.columns

def plot(df,col): fig,(ax1,ax2)=plt.subplots(2,1) sns.distplot(df[col],ax=ax1) sns.boxplot(df[col],ax=ax2)

plt.figure(figsize=(30,20)) plot(data_train,'Price')

data_train['Price']=np.where(data_train['Price']>=40000,data_train['Price'].median(),data_train['Price'])

plt.figure(figsize=(30,20)) plot(data_train,'Price')

X=data_train.drop('Price',axis=1) X.head()

y=data_train['Price'] y

type(X)

type(y)

X.isnull().sum()

y.isnull().sum()

np.array(X)

np.array(y)

from sklearn.feature_selection import mutual_info_classif

X.dtypes

mutual_info_classif(X,y)

imp=pd.DataFrame(mutual_info_classif(X,y),index=X.columns) imp

imp.columns=['importance'] imp.sort_values(by='importance',ascending=False)

from sklearn.model_selection import train_test_split

X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)

from sklearn import metrics ## Dump your model using pickle so that we will re-use import pickle def predict(ml_model,dump): model=ml_model.fit(X_train,y_train) print('Training score : {}'.format(model.score(X_train,y_train))) y_prediction=model.predict(X_test) print('Predictions are: \n {}'.format(y_prediction)) print('\n') r2_score=metrics.r2_score(y_test,y_prediction) print('r2 score: {}'.format(r2_score)) print('MAE:',metrics.mean_absolute_error(y_test,y_prediction)) print('MSE:',metrics.mean_squared_error(y_test,y_prediction)) print('RMSE:',np.sqrt(metrics.mean_squared_error(y_test,y_prediction))) sns.distplot(y_test-y_prediction) if dump==1: ##dump your model using pickle so that we will re-use file=open('/content/model.pkl','wb') pickle.dump(model,file)

from sklearn.ensemble import RandomForestRegressor

predict(RandomForestRegressor(),1)

from sklearn.linear_model import LinearRegression from sklearn.neighbors import KNeighborsRegressor from sklearn.ensemble import RandomForestRegressor from sklearn.tree import DecisionTreeRegressor

predict(DecisionTreeRegressor(),0)

predict(LinearRegression(),0)

predict(KNeighborsRegressor(),0)

from sklearn.model_selection import RandomizedSearchCV

# Number of trees in random forest n_estimators=[int(x) for x in np.linspace(start=100,stop=1200,num=6)] # Number of features to consider at every split max_features=['auto','sqrt'] # Maximum number of levels in tree max_depth=[int(x) for x in np.linspace(5,30,num=4)] # Minimum number of samples required to split a node min_samples_split=[5,10,15,100]

# Create the random grid random_grid={ 'n_estimators':n_estimators, 'max_features':max_features, 'max_depth':max_depth, 'min_samples_split':min_samples_split }

random_grid

### initialise your estimator reg_rf=RandomForestRegressor()

# Random search of parameters, using 3 fold cross validation rf_random=RandomizedSearchCV(estimator=reg_rf,param_distributions=random_grid,cv=3,verbose=2,n_jobs=-1)

rf_random.fit(X_train,y_train)

rf_random.best_params_

prediction=rf_random.predict(X_test) prediction

sns.distplot(y_test-prediction)

metrics.r2_score(y_test,prediction)

print('MAE',metrics.mean_absolute_error(y_test,prediction)) print('MSE',metrics.mean_squared_error(y_test,prediction)) print('RMSE',np.sqrt(metrics.mean_squared_error(y_test,prediction)))

!pip install pickle

import pickle

# Open a file, where you want to store the data file=open('rf_random.pkl','wb')

# Dump information to that file pickle.dump(rf_random,file)

model=open('rf_random.pkl','rb') forest=pickle.load(model)

y_prediction=forest.predict(X_test)

y_prediction

metrics.r2_score(y_test,y_prediction)