{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nimport matplotlib.colors\nfrom matplotlib.ticker import MultipleLocator, FormatStrFormatter\nimport plotly.express as px\nimport plotly.graph_objects as go\nfrom plotly.subplots import make_subplots\nfrom plotly.offline import init_notebook_mode\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.model_selection import StratifiedKFold \nfrom sklearn.metrics import roc_auc_score, roc_curve, auc\nimport catboost\nfrom catboost import Pool\nfrom catboost import CatBoostRegressor\nfrom xgboost import XGBRegressor\nfrom xgboost import plot_importance\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.preprocessing import StandardScaler, MinMaxScaler\nfrom sklearn.impute import SimpleImputer\n\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:01.702632Z","iopub.execute_input":"2022-07-30T15:15:01.703027Z","iopub.status.idle":"2022-07-30T15:15:01.713570Z","shell.execute_reply.started":"2022-07-30T15:15:01.702995Z","shell.execute_reply":"2022-07-30T15:15:01.712285Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Let's explore which variable is the most important factor affecting whether a passenger will be sent to another dimension!","metadata":{}},{"cell_type":"code","source":"#load data\ntrain = pd.read_csv(\"../input/spaceship-titanic/train.csv\")\ntest = pd.read_csv(\"../input/spaceship-titanic/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:01.837689Z","iopub.execute_input":"2022-07-30T15:15:01.838791Z","iopub.status.idle":"2022-07-30T15:15:01.896535Z","shell.execute_reply.started":"2022-07-30T15:15:01.838736Z","shell.execute_reply":"2022-07-30T15:15:01.895224Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Data Preprocessing","metadata":{}},{"cell_type":"markdown","source":"checking the type of data and missing data","metadata":{}},{"cell_type":"code","source":"train.info()","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:02.105304Z","iopub.execute_input":"2022-07-30T15:15:02.106979Z","iopub.status.idle":"2022-07-30T15:15:02.132731Z","shell.execute_reply.started":"2022-07-30T15:15:02.106929Z","shell.execute_reply":"2022-07-30T15:15:02.131389Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:02.213178Z","iopub.execute_input":"2022-07-30T15:15:02.213581Z","iopub.status.idle":"2022-07-30T15:15:02.232369Z","shell.execute_reply.started":"2022-07-30T15:15:02.213550Z","shell.execute_reply":"2022-07-30T15:15:02.231091Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.info()","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:02.344790Z","iopub.execute_input":"2022-07-30T15:15:02.345503Z","iopub.status.idle":"2022-07-30T15:15:02.365104Z","shell.execute_reply.started":"2022-07-30T15:15:02.345466Z","shell.execute_reply":"2022-07-30T15:15:02.363205Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:02.466488Z","iopub.execute_input":"2022-07-30T15:15:02.466936Z","iopub.status.idle":"2022-07-30T15:15:02.480054Z","shell.execute_reply.started":"2022-07-30T15:15:02.466899Z","shell.execute_reply":"2022-07-30T15:15:02.478899Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"change 'CryoSleep', 'VIP' and 'Transported' into 0 and 1","metadata":{}},{"cell_type":"code","source":"train['CryoSleep']=train['CryoSleep'].astype(str)\ntrain['VIP']=train['VIP'].astype(str)\n\ntest['CryoSleep']=test['CryoSleep'].astype(str)\ntest['VIP']=test['VIP'].astype(str)\n","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:02.513916Z","iopub.execute_input":"2022-07-30T15:15:02.514947Z","iopub.status.idle":"2022-07-30T15:15:02.535544Z","shell.execute_reply.started":"2022-07-30T15:15:02.514900Z","shell.execute_reply":"2022-07-30T15:15:02.533683Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['Transported']=train['Transported'].astype(int)\n\ntrain['CryoSleep'].replace('False',0,inplace=True)\ntrain['CryoSleep'].replace('True',1,inplace=True)\ntrain['VIP'].replace('False',0,inplace=True)\ntrain['VIP'].replace('True',1,inplace=True)\n\ntest['CryoSleep'].replace('False',0,inplace=True)\ntest['CryoSleep'].replace('True',1,inplace=True)\ntest['VIP'].replace('False',0,inplace=True)\ntest['VIP'].replace('True',1,inplace=True)","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:02.575911Z","iopub.execute_input":"2022-07-30T15:15:02.576539Z","iopub.status.idle":"2022-07-30T15:15:02.594676Z","shell.execute_reply.started":"2022-07-30T15:15:02.576503Z","shell.execute_reply":"2022-07-30T15:15:02.593365Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Deal with missing data**","metadata":{}},{"cell_type":"markdown","source":"Since People in a group are often family members(not always), we can use PassengerId to fill in their last name.","metadata":{}},{"cell_type":"code","source":"#split PassengerId and Name to get group number and last name\ntrain['gggg']=train['PassengerId'].str.split('_', 1).str[0]\ntrain['pp']=train['PassengerId'].str.split('_', 1).str[1]\ntrain['firstname']=train['Name'].str.split(' ',1).str[0]\ntrain['lastname']=train['Name'].str.split(' ',1).str[1]\ntrain['Cabin_desk']=train['Cabin'].str.split('/',1).str[0]\ntrain['Cabin_num']=train['Cabin'].str.split('/',1).str[1]\ntrain['Cabin_side']=train['Cabin_num'].str.split('/',1).str[1]\ntrain['Cabin_num']=train['Cabin_num'].str.split('/',1).str[0]\ntrain.drop('Cabin',axis=1,inplace=True)\ntrain.drop('Name',axis=1,inplace=True)\n\ntest['gggg']=test['PassengerId'].str.split('_', 1).str[0]\ntest['pp']=test['PassengerId'].str.split('_', 1).str[1]\ntest['firstname']=test['Name'].str.split(' ',1).str[0]\ntest['lastname']=test['Name'].str.split(' ',1).str[1]\ntest['Cabin_desk']=test['Cabin'].str.split('/',1).str[0]\ntest['Cabin_num']=test['Cabin'].str.split('/',1).str[1]\ntest['Cabin_side']=test['Cabin_num'].str.split('/',1).str[1]\ntest['Cabin_num']=test['Cabin_num'].str.split('/',1).str[0]\ntest.drop('Name',axis=1,inplace=True)\ntest.drop('Cabin',axis=1,inplace=True)\n","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:02.632153Z","iopub.execute_input":"2022-07-30T15:15:02.632849Z","iopub.status.idle":"2022-07-30T15:15:02.899245Z","shell.execute_reply.started":"2022-07-30T15:15:02.632785Z","shell.execute_reply":"2022-07-30T15:15:02.897857Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['firstname'].fillna('missing',inplace=True)\ntrain['lastname'].fillna('missing',inplace=True)\nfor i in range(train.shape[0]):\n if train.iloc[i,16]=='missing':\n if train.iloc[i,13]==train.iloc[(i-1),13]:\n train.iloc[i,16]=train.iloc[(i-1),16]\n elif train.iloc[i,13]==train.iloc[(i+1),13]:\n train.iloc[i,16]=train.iloc[(i+1),16]","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:02.904293Z","iopub.execute_input":"2022-07-30T15:15:02.904679Z","iopub.status.idle":"2022-07-30T15:15:03.249199Z","shell.execute_reply.started":"2022-07-30T15:15:02.904650Z","shell.execute_reply":"2022-07-30T15:15:03.247890Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test['firstname'].fillna('missing',inplace=True)\ntest['lastname'].fillna('missing',inplace=True)\nfor i in range(test.shape[0]):\n if test.iloc[i,15]=='missing':\n if test.iloc[i,12]==test.iloc[(i-1),12]:\n test.iloc[i,15]=test.iloc[(i-1),15]\n elif test.iloc[i,12]==test.iloc[(i+1),12]:\n test.iloc[i,15]=test.iloc[(i+1),15]","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:03.250573Z","iopub.execute_input":"2022-07-30T15:15:03.250996Z","iopub.status.idle":"2022-07-30T15:15:03.424786Z","shell.execute_reply.started":"2022-07-30T15:15:03.250959Z","shell.execute_reply":"2022-07-30T15:15:03.423595Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Use numbers to represent different categories","metadata":{}},{"cell_type":"code","source":"#To plot the pie chart of HomePlanet and Destination, we do dummies later\n#train=pd.get_dummies(train,columns=['HomePlanet','Destination'])\n#test=pd.get_dummies(test,columns=['HomePlanet','Destination'])","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:03.428007Z","iopub.execute_input":"2022-07-30T15:15:03.428381Z","iopub.status.idle":"2022-07-30T15:15:03.434294Z","shell.execute_reply.started":"2022-07-30T15:15:03.428349Z","shell.execute_reply":"2022-07-30T15:15:03.432891Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def ABC(x):\n if x == 'A':\n return 1\n elif x=='B':\n return 2\n elif x=='C':\n return 3\n elif x=='D':\n return 4\n elif x=='E':\n return 5\n elif x=='F':\n return 6\n elif x=='G':\n return 7\n elif x=='T':\n return 8\n ","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:03.435704Z","iopub.execute_input":"2022-07-30T15:15:03.436129Z","iopub.status.idle":"2022-07-30T15:15:03.454141Z","shell.execute_reply.started":"2022-07-30T15:15:03.436046Z","shell.execute_reply":"2022-07-30T15:15:03.452739Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['Cabin_side'].replace('P',0,inplace=True)\ntrain['Cabin_side'].replace('S',1,inplace=True)\ntest['Cabin_side'].replace('P',0,inplace=True)\ntest['Cabin_side'].replace('S',1,inplace=True)\n\ntrain['Cabin_desk']=train['Cabin_desk'].map(ABC)\ntest['Cabin_desk']=test['Cabin_desk'].map(ABC)","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:03.456047Z","iopub.execute_input":"2022-07-30T15:15:03.456390Z","iopub.status.idle":"2022-07-30T15:15:03.495857Z","shell.execute_reply.started":"2022-07-30T15:15:03.456360Z","shell.execute_reply":"2022-07-30T15:15:03.494381Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Since the dataframe is sort by PassengerId, and the next person is usually a family member or friend of the person at the front. So we use 'bfill' to fill in object variables(variables about seat, destination and so on), which are always similar to their friend.","metadata":{}},{"cell_type":"code","source":"train['VIP'].replace('nan', 0, inplace=True)\ntest['VIP'].replace('nan', 0, inplace=True)\n\ntrain['CryoSleep'].replace('nan', 0, inplace=True)\ntest['CryoSleep'].replace('nan', 0, inplace=True)","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:03.497976Z","iopub.execute_input":"2022-07-30T15:15:03.498568Z","iopub.status.idle":"2022-07-30T15:15:03.528707Z","shell.execute_reply.started":"2022-07-30T15:15:03.498521Z","shell.execute_reply":"2022-07-30T15:15:03.527774Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for columns in train.columns:\n if train[columns].dtype==object:\n train[columns].fillna(method='bfill',inplace=True)\n else:\n train[columns].fillna(train[columns].mean(),inplace=True)\n \nfor columns in test.columns:\n if test[columns].dtype==object:\n test[columns].fillna(method='bfill',inplace=True)\n else:\n test[columns].fillna(test[columns].mean(),inplace=True)","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:03.529901Z","iopub.execute_input":"2022-07-30T15:15:03.531069Z","iopub.status.idle":"2022-07-30T15:15:03.573910Z","shell.execute_reply.started":"2022-07-30T15:15:03.531018Z","shell.execute_reply":"2022-07-30T15:15:03.572611Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ntrain['Cabin_num'].fillna(method='bfill',inplace=True)\ntrain['Cabin_num']=train['Cabin_num'].astype(int)\ntrain['Cabin_desk']=train['Cabin_desk'].astype(int)\ntrain['Cabin_side']=train['Cabin_side'].astype(int)\n\ntest['Cabin_num'].fillna(method='bfill',inplace=True)\ntest['Cabin_num']=test['Cabin_num'].astype(int)\ntest['Cabin_desk']=test['Cabin_desk'].astype(int)\ntest['Cabin_side']=test['Cabin_side'].astype(int)","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:03.576534Z","iopub.execute_input":"2022-07-30T15:15:03.577205Z","iopub.status.idle":"2022-07-30T15:15:03.599287Z","shell.execute_reply.started":"2022-07-30T15:15:03.577154Z","shell.execute_reply":"2022-07-30T15:15:03.598027Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Cabin_num may be given according to the location of the seat, we can divide them into 4 different zone.","metadata":{}},{"cell_type":"code","source":"def LOC(x):\n if x <= 450:\n return 0\n elif 450 < x <=900:\n return 1\n elif 900 < x <= 1350:\n return 2\n elif x>1350:\n return 3\n ","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:03.602512Z","iopub.execute_input":"2022-07-30T15:15:03.602919Z","iopub.status.idle":"2022-07-30T15:15:03.610369Z","shell.execute_reply.started":"2022-07-30T15:15:03.602885Z","shell.execute_reply":"2022-07-30T15:15:03.609108Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['Cabin_zone']=train['Cabin_num'].map(LOC)\ntest['Cabin_zone']=test['Cabin_num'].map(LOC)","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:03.611879Z","iopub.execute_input":"2022-07-30T15:15:03.612753Z","iopub.status.idle":"2022-07-30T15:15:03.634025Z","shell.execute_reply.started":"2022-07-30T15:15:03.612715Z","shell.execute_reply":"2022-07-30T15:15:03.633124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# EDA","metadata":{}},{"cell_type":"markdown","source":"Now, let's summarize the meaning of each columns:\n* PassengerId(unique)\n* CryoSleep: Indicates whether the passenger elected to be put into suspended animation for the duration of the voyage.(0:False,1:True)\n* Age\n* VIP: Whether the passenger has paid for special VIP service during the voyage.(0:False,1:True)\n* RoomService, FoodCourt, ShoppingMall, Spa, VRDeck: Amount the passenger has billed at each of the Spaceship Titanic's many luxury amenities.\n* Cabin_desk: which desk the passenger was in. (change alphabet to number)\n* Cabin_num: the cabin number.\n* Cabin_side: which side the passenger was in,P for Port or S for Starboard.(0:P,1:S)\n* HomePlanet_Earth, HomePlanet_Europa, HomePlanet_Mars: One-Hot encoding of the planet the passenger departed from.\n* Destination_55 Cancri e, Destination_PSO J318.5-22, Destination_TRAPPIST-1e: One-Hot encoding of the planet the passenger will be debarking to.","metadata":{}},{"cell_type":"code","source":"temp=dict(layout=go.Layout(font=dict(family=\"Franklin Gothic\", size=12), \n height=500, width=1000))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:03.635138Z","iopub.execute_input":"2022-07-30T15:15:03.635474Z","iopub.status.idle":"2022-07-30T15:15:03.654438Z","shell.execute_reply.started":"2022-07-30T15:15:03.635443Z","shell.execute_reply":"2022-07-30T15:15:03.652957Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.style.use('ggplot')\nf, (ax1, ax2,ax3) = plt.subplots(1,3,figsize=(75, 25),dpi=100)\nax1.boxplot(x = train['Age'])\nax1.set_title('Overall Distribution',fontsize=30)\nax1.tick_params(labelsize=30)\n\ndf=train.loc[train['Transported']==0,:]\nax2.boxplot(x = df['Age'])\nax2.set_title('Not Transported Distribution',fontsize=30)\nax2.tick_params(labelsize=30)\n\ndf=train.loc[train['Transported']==1,:]\nax3.boxplot(x = df['Age'])\nax3.set_title('Transported Distribution',fontsize=30)\nax3.tick_params(labelsize=30)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:03.656273Z","iopub.execute_input":"2022-07-30T15:15:03.656731Z","iopub.status.idle":"2022-07-30T15:15:04.926476Z","shell.execute_reply.started":"2022-07-30T15:15:03.656694Z","shell.execute_reply":"2022-07-30T15:15:04.925102Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Most of the passengers are young adults in their 20s and 30s, and there are very few children and elderly among the passengers. The age distribution of all passengers, not transported passengers and transported passengers are very similar, whether transported or not may has nothing to do with age.","metadata":{}},{"cell_type":"code","source":"target=train.Transported.value_counts(normalize=True)\ntarget.rename(index={1:'True',0:'False'},inplace=True)\npal, color=['aliceblue','mistyrose','cornsilk','honeydew','plum'], ['skyblue','salmon','gold','darkseagreen','blueviolet']\nfig=go.Figure()\nfig.add_trace(go.Pie(labels=target.index, values=target*100, hole=.45, \n showlegend=True,sort=False, \n marker=dict(colors=color,line=dict(color=pal,width=2.5)),\n hovertemplate = \"%{label} Accounts: %{value:.2f}%\"))\nfig.update_layout(template=temp, title='Transport state Distribution', \n legend=dict(traceorder='reversed',y=1.05,x=0),\n uniformtext_minsize=15, uniformtext_mode='hide',width=700)\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:04.930048Z","iopub.execute_input":"2022-07-30T15:15:04.930428Z","iopub.status.idle":"2022-07-30T15:15:04.956359Z","shell.execute_reply.started":"2022-07-30T15:15:04.930396Z","shell.execute_reply":"2022-07-30T15:15:04.955467Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The number of passengers who have been transported to another dimension is almost the same as those who haven't been.","metadata":{}},{"cell_type":"code","source":"target=train.VIP.value_counts(normalize=True)\ntarget.rename(index={1:'True',0:'False'},inplace=True)\npal, color=['aliceblue','cornsilk','honeydew','plum'], ['skyblue','gold','darkseagreen','blueviolet']\nfig=go.Figure()\nfig.add_trace(go.Pie(labels=target.index, values=target*100, hole=.45, \n showlegend=True,sort=False, \n marker=dict(colors=color,line=dict(color=pal,width=2.5)),\n hovertemplate = \"%{label} Accounts: %{value:.2f}%\"))\nfig.update_layout(template=temp, title='VIP Distribution', \n legend=dict(traceorder='reversed',y=1.05,x=0),\n uniformtext_minsize=15, uniformtext_mode='hide',width=700)\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:04.957605Z","iopub.execute_input":"2022-07-30T15:15:04.958681Z","iopub.status.idle":"2022-07-30T15:15:04.981958Z","shell.execute_reply.started":"2022-07-30T15:15:04.958645Z","shell.execute_reply":"2022-07-30T15:15:04.980652Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Most of the passengers are NOT VIP, only 2.29% of them are VIP.","metadata":{}},{"cell_type":"code","source":"target=train.loc[:,['VIP','Transported']]\ntarget['Transported']=target['Transported'].astype(object)\ntarget['VIP']=target['VIP'].astype(object)\ntarget=pd.get_dummies(target,columns=['Transported'])\ntarget=target.groupby('VIP',as_index=False).agg('sum')\npal, color=['aliceblue','mistyrose','cornsilk','honeydew','plum'], ['skyblue','salmon','gold','darkseagreen','blueviolet']\nrgb=['rgba'+str(matplotlib.colors.to_rgba(i,0.7)) for i in pal]\nfig=go.Figure()\nfig.add_trace(go.Bar(x=target.VIP, y=target.Transported_1, name='True',\n text=target.Transported_1, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[0],line=dict(color=pal[0],width=1.5)),\n hovertemplate = \"%{x}
True accounts: %{y:.2f}\"))\nfig.add_trace(go.Bar(x=target.VIP, y=target.Transported_0, name='False',\n text=target.Transported_0, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[2],line=dict(color=pal[2],width=1.5)),\n hovertemplate = \"%{x}
False accounts: %{y:.2f}\"))\nfig.update_layout(template=temp,title='Distribution of Transported', \n barmode='relative', width=1400,\n legend=dict(orientation=\"h\", traceorder=\"reversed\", yanchor=\"bottom\",y=1.1,xanchor=\"left\", x=0))\nfig.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:04.983496Z","iopub.execute_input":"2022-07-30T15:15:04.984312Z","iopub.status.idle":"2022-07-30T15:15:05.026448Z","shell.execute_reply.started":"2022-07-30T15:15:04.984276Z","shell.execute_reply":"2022-07-30T15:15:05.025350Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"target=train.CryoSleep.value_counts(normalize=True)\ntarget.rename(index={1:'True',0:'False'},inplace=True)\npal, color=['seashell','aliceblue','mistyrose','cornsilk','honeydew','plum'], ['sandybrown','skyblue','salmon','gold','darkseagreen','blueviolet']\nfig=go.Figure()\nfig.add_trace(go.Pie(labels=target.index, values=target*100, hole=.45, \n showlegend=True,sort=False, \n marker=dict(colors=color,line=dict(color=pal,width=2.5)),\n hovertemplate = \"%{label} Accounts: %{value:.2f}%\"))\nfig.update_layout(template=temp, title='CryoSleep Distribution', \n legend=dict(traceorder='reversed',y=1.05,x=0),\n uniformtext_minsize=15, uniformtext_mode='hide',width=700)\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.028106Z","iopub.execute_input":"2022-07-30T15:15:05.028437Z","iopub.status.idle":"2022-07-30T15:15:05.053501Z","shell.execute_reply.started":"2022-07-30T15:15:05.028403Z","shell.execute_reply":"2022-07-30T15:15:05.052441Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Many people are elected to be put into suspended animation, which is almost twice as many as those who are not elected.","metadata":{}},{"cell_type":"code","source":"target=train.loc[:,['CryoSleep','Transported']]\ntarget['Transported']=target['Transported'].astype(object)\ntarget['CryoSleep']=target['CryoSleep'].astype(object)\ntarget=pd.get_dummies(target,columns=['Transported'])\ntarget=target.groupby('CryoSleep',as_index=False).agg('sum')\n\nrgb=['rgba'+str(matplotlib.colors.to_rgba(i,0.7)) for i in pal]\nfig=go.Figure()\nfig.add_trace(go.Bar(x=target.CryoSleep, y=target.Transported_1, name='True',\n text=target.Transported_1, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[4],line=dict(color=pal[4],width=1.5)),\n hovertemplate = \"%{x}
True accounts: %{y:.2f}\"))\nfig.add_trace(go.Bar(x=target.CryoSleep, y=target.Transported_0, name='False',\n text=target.Transported_0, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[3],line=dict(color=pal[3],width=1.5)),\n hovertemplate = \"%{x}
False accounts: %{y:.2f}\"))\nfig.update_layout(template=temp,title='Distribution of Transported', \n barmode='relative', width=1400,\n legend=dict(orientation=\"h\", traceorder=\"reversed\", yanchor=\"bottom\",y=1.1,xanchor=\"left\", x=0))\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.054675Z","iopub.execute_input":"2022-07-30T15:15:05.055484Z","iopub.status.idle":"2022-07-30T15:15:05.097209Z","shell.execute_reply.started":"2022-07-30T15:15:05.055448Z","shell.execute_reply":"2022-07-30T15:15:05.095967Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" Passengers who choose to be CryoSleep are more likely to be sent to another dimension.","metadata":{}},{"cell_type":"code","source":"target=train.HomePlanet.value_counts(normalize=True)\ntarget.rename(index={1:'True',0:'False'},inplace=True)\npal, color=['aliceblue','mistyrose','cornsilk','honeydew','plum'], ['skyblue','salmon','gold','darkseagreen','blueviolet']\nfig=go.Figure()\nfig.add_trace(go.Pie(labels=target.index, values=target*100, hole=.45, \n showlegend=True,sort=False, \n marker=dict(colors=color,line=dict(color=pal,width=2.5)),\n hovertemplate = \"%{label} Accounts: %{value:.2f}%\"))\nfig.update_layout(template=temp, title='HomePlanet Distribution', \n legend=dict(traceorder='reversed',y=1.05,x=0),\n uniformtext_minsize=15, uniformtext_mode='hide',width=700)\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.098999Z","iopub.execute_input":"2022-07-30T15:15:05.099476Z","iopub.status.idle":"2022-07-30T15:15:05.129495Z","shell.execute_reply.started":"2022-07-30T15:15:05.099430Z","shell.execute_reply":"2022-07-30T15:15:05.128288Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"target=train.loc[:,['HomePlanet','Transported']]\ntarget['Transported']=target['Transported'].astype(object)\ntarget=pd.get_dummies(target,columns=['Transported'])\ntarget=target.groupby('HomePlanet',as_index=False).agg('sum')\n\npal, color=['seashell','aliceblue','mistyrose','cornsilk','honeydew','plum'], ['sandybrown','skyblue','salmon','gold','darkseagreen','blueviolet']\nrgb=['rgba'+str(matplotlib.colors.to_rgba(i,0.7)) for i in pal]\nfig=go.Figure()\nfig.add_trace(go.Bar(x=target.HomePlanet, y=target.Transported_1, name='True',\n text=target.Transported_1, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[5],line=dict(color=pal[5],width=1.5)),\n hovertemplate = \"%{x}
True accounts: %{y:.2f}\"))\nfig.add_trace(go.Bar(x=target.HomePlanet, y=target.Transported_0, name='False',\n text=target.Transported_0, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[3],line=dict(color=pal[3],width=1.5)),\n hovertemplate = \"%{x}
False accounts: %{y:.2f}\"))\nfig.update_layout(template=temp,title='Distribution of Transported', \n barmode='relative', width=1400,\n legend=dict(orientation=\"h\", traceorder=\"reversed\", yanchor=\"bottom\",y=1.1,xanchor=\"left\", x=0))\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.131548Z","iopub.execute_input":"2022-07-30T15:15:05.132948Z","iopub.status.idle":"2022-07-30T15:15:05.175404Z","shell.execute_reply.started":"2022-07-30T15:15:05.132895Z","shell.execute_reply":"2022-07-30T15:15:05.174434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The probability that a person from Europe will be transport is the highest among all, which is 66%.","metadata":{}},{"cell_type":"code","source":"target=train.Destination.value_counts(normalize=True)\ntarget.rename(index={1:'True',0:'False'},inplace=True)\npal, color=['aliceblue','cornsilk','honeydew','plum'], ['skyblue','gold','darkseagreen','blueviolet']\nfig=go.Figure()\nfig.add_trace(go.Pie(labels=target.index, values=target*100, hole=.45, \n showlegend=True,sort=False, \n marker=dict(colors=color,line=dict(color=pal,width=2.5)),\n hovertemplate = \"%{label} Accounts: %{value:.2f}%\"))\nfig.update_layout(template=temp, title='Destination Distribution', \n legend=dict(traceorder='reversed',y=1.05,x=0),\n uniformtext_minsize=15, uniformtext_mode='hide',width=700)\nfig.show()\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.176533Z","iopub.execute_input":"2022-07-30T15:15:05.177154Z","iopub.status.idle":"2022-07-30T15:15:05.205780Z","shell.execute_reply.started":"2022-07-30T15:15:05.177114Z","shell.execute_reply":"2022-07-30T15:15:05.204275Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"target=train.loc[:,['Destination','Transported']]\ntarget['Transported']=target['Transported'].astype(object)\ntarget=pd.get_dummies(target,columns=['Transported'])\ntarget=target.groupby('Destination',as_index=False).agg('sum')\n\n\npal, color=['seashell','aliceblue','mistyrose','cornsilk','honeydew','plum'], ['sandybrown','skyblue','salmon','gold','darkseagreen','blueviolet']\nrgb=['rgba'+str(matplotlib.colors.to_rgba(i,0.7)) for i in pal]\nfig=go.Figure()\nfig.add_trace(go.Bar(x=target.Destination, y=target.Transported_1, name='True',\n text=target.Transported_1, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[2],line=dict(color=pal[2],width=1.5)),\n hovertemplate = \"%{x}
True accounts: %{y:.2f}\"))\nfig.add_trace(go.Bar(x=target.Destination, y=target.Transported_0, name='False',\n text=target.Transported_0, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[0],line=dict(color=pal[0],width=1.5)),\n hovertemplate = \"%{x}
False accounts: %{y:.2f}\"))\nfig.update_layout(template=temp,title='Distribution of Transported', \n barmode='relative', width=1400,\n legend=dict(orientation=\"h\", traceorder=\"reversed\", yanchor=\"bottom\",y=1.1,xanchor=\"left\", x=0))\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.210638Z","iopub.execute_input":"2022-07-30T15:15:05.211488Z","iopub.status.idle":"2022-07-30T15:15:05.257567Z","shell.execute_reply.started":"2022-07-30T15:15:05.211431Z","shell.execute_reply":"2022-07-30T15:15:05.256246Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The probability of 55Cancri e is a litte bit higher than others as well as overall probability, which is 61%.","metadata":{}},{"cell_type":"code","source":"train=pd.get_dummies(train,columns=['HomePlanet','Destination'])\ntest=pd.get_dummies(test,columns=['HomePlanet','Destination'])","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:05.259025Z","iopub.execute_input":"2022-07-30T15:15:05.259592Z","iopub.status.idle":"2022-07-30T15:15:05.287002Z","shell.execute_reply.started":"2022-07-30T15:15:05.259558Z","shell.execute_reply":"2022-07-30T15:15:05.285563Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"target=train.loc[:,['Cabin_desk','Transported']]\ntarget['Transported']=target['Transported'].astype(object)\ntarget=pd.get_dummies(target,columns=['Transported'])\ntarget=target.groupby('Cabin_desk',as_index=False).agg('sum')","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.289697Z","iopub.execute_input":"2022-07-30T15:15:05.290381Z","iopub.status.idle":"2022-07-30T15:15:05.310065Z","shell.execute_reply.started":"2022-07-30T15:15:05.290345Z","shell.execute_reply":"2022-07-30T15:15:05.308435Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pal, color=['seashell','aliceblue','mistyrose','cornsilk','honeydew','plum'], ['sandybrown','skyblue','salmon','gold','darkseagreen','blueviolet']\nrgb=['rgba'+str(matplotlib.colors.to_rgba(i,0.7)) for i in pal]\nfig=go.Figure()\nfig.add_trace(go.Bar(x=target.Cabin_desk, y=target.Transported_1, name='True',\n text=target.Transported_1, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[5],line=dict(color=pal[5],width=1.5)),\n hovertemplate = \"%{x}
True accounts: %{y:.2f}\"))\nfig.add_trace(go.Bar(x=target.Cabin_desk, y=target.Transported_0, name='False',\n text=target.Transported_0, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[3],line=dict(color=pal[3],width=1.5)),\n hovertemplate = \"%{x}
False accounts: %{y:.2f}\"))\nfig.update_layout(template=temp,title='Distribution of Transported in different Cabin_desk', \n barmode='relative', width=1400,\n legend=dict(orientation=\"h\", traceorder=\"reversed\", yanchor=\"bottom\",y=1.1,xanchor=\"left\", x=0))\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.311693Z","iopub.execute_input":"2022-07-30T15:15:05.312539Z","iopub.status.idle":"2022-07-30T15:15:05.344536Z","shell.execute_reply.started":"2022-07-30T15:15:05.312500Z","shell.execute_reply":"2022-07-30T15:15:05.343391Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"target=train.loc[:,['Cabin_side','Transported']]\ntarget['Transported']=target['Transported'].astype(object)\ntarget['Cabin_side']=target['Cabin_side'].astype(object)\ntarget=pd.get_dummies(target,columns=['Transported'])\ntarget=target.groupby('Cabin_side',as_index=False).agg('sum')\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.345736Z","iopub.execute_input":"2022-07-30T15:15:05.346885Z","iopub.status.idle":"2022-07-30T15:15:05.373960Z","shell.execute_reply.started":"2022-07-30T15:15:05.346839Z","shell.execute_reply":"2022-07-30T15:15:05.372758Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"rgb=['rgba'+str(matplotlib.colors.to_rgba(i,0.7)) for i in pal]\nfig=go.Figure()\nfig.add_trace(go.Bar(x=target.Cabin_side, y=target.Transported_1, name='True',\n text=target.Transported_1, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[4],line=dict(color=pal[4],width=1.5)),\n hovertemplate = \"%{x}
True accounts: %{y:.2f}\"))\nfig.add_trace(go.Bar(x=target.Cabin_side, y=target.Transported_0, name='False',\n text=target.Transported_0, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=color[3],line=dict(color=pal[3],width=1.5)),\n hovertemplate = \"%{x}
False accounts: %{y:.2f}\"))\nfig.update_layout(template=temp,title='Distribution of Transported in different Cabin_side', \n barmode='relative', width=1400,\n legend=dict(orientation=\"h\", traceorder=\"reversed\", yanchor=\"bottom\",y=1.1,xanchor=\"left\", x=0))\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.375252Z","iopub.execute_input":"2022-07-30T15:15:05.376194Z","iopub.status.idle":"2022-07-30T15:15:05.408912Z","shell.execute_reply.started":"2022-07-30T15:15:05.376155Z","shell.execute_reply":"2022-07-30T15:15:05.407691Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"target=train.loc[:,['Cabin_zone','Transported']]\ntarget['Transported']=target['Transported'].astype(object)\ntarget=pd.get_dummies(target,columns=['Transported'])","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.410535Z","iopub.execute_input":"2022-07-30T15:15:05.410961Z","iopub.status.idle":"2022-07-30T15:15:05.437898Z","shell.execute_reply.started":"2022-07-30T15:15:05.410923Z","shell.execute_reply":"2022-07-30T15:15:05.436673Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"rgb=['rgba'+str(matplotlib.colors.to_rgba(i,0.7)) for i in pal]\nfig=go.Figure()\nfig.add_trace(go.Bar(x=target.Cabin_zone, y=target.Transported_1, name='True',\n text=target.Transported_1, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=pal[5],line=dict(color=color[5],width=1.5)),\n hovertemplate = \"%{x}
True accounts: %{y:.2f}\"))\nfig.add_trace(go.Bar(x=target.Cabin_zone, y=target.Transported_0, name='False',\n text=target.Transported_0, texttemplate='%{text:.0f}', \n textposition='inside',insidetextanchor=\"middle\",\n marker=dict(color=pal[3],line=dict(color=color[3],width=1.5)),\n hovertemplate = \"%{x}
False accounts: %{y:.2f}\"))\nfig.update_layout(template=temp,title='Distribution of Transported in different Cabin_zone', \n barmode='relative', width=1400,\n legend=dict(orientation=\"h\", traceorder=\"reversed\", yanchor=\"bottom\",y=1.1,xanchor=\"left\", x=0))\nfig.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.439470Z","iopub.execute_input":"2022-07-30T15:15:05.439875Z","iopub.status.idle":"2022-07-30T15:15:05.477489Z","shell.execute_reply.started":"2022-07-30T15:15:05.439839Z","shell.execute_reply":"2022-07-30T15:15:05.474623Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The probabilities that whether a person was transported in every area(Cabin_num, Cabin_desk, Cabin_zone) are very close (40%~50%), except in Cabin_desk=2,3, the probability is about 70%.","metadata":{}},{"cell_type":"code","source":"Room=train.loc[:,['RoomService','Transported']]\nFood=train.loc[:,['FoodCourt','Transported']]\nshop=train.loc[:,['ShoppingMall','Transported']]\nspa=train.loc[:,['Spa','Transported']]\nvr=train.loc[:,['VRDeck','Transported']]\n\nRoom['consume_state']=0\nRoom.loc[Room['RoomService']>0,['consume_state']]=1\n\nFood['consume_state']=0\nFood.loc[Food['FoodCourt']>0,['consume_state']]=1\n\nshop['consume_state']=0\nshop.loc[shop['ShoppingMall']>0,['consume_state']]=1\n\nspa['consume_state']=0\nspa.loc[spa['Spa']>0,['consume_state']]=1\n\nvr['consume_state']=0\nvr.loc[vr['VRDeck']>0,['consume_state']]=1","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.479909Z","iopub.execute_input":"2022-07-30T15:15:05.480302Z","iopub.status.idle":"2022-07-30T15:15:05.509456Z","shell.execute_reply.started":"2022-07-30T15:15:05.480267Z","shell.execute_reply":"2022-07-30T15:15:05.508555Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.style.use('ggplot')\nf, (ax1, ax2,ax3,ax4,ax5) = plt.subplots(1, 5,figsize=(20, 10),dpi=100)\na=Room['consume_state'].sum()\nb=len(Room['consume_state'])-a\nax1.pie([a,b],labels=['consume','not consume'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax1.set_title('RoomService')\n\na=Food['consume_state'].sum()\nb=len(Food['consume_state'])-a\nax2.pie([a,b],labels=['consume','not consume'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax2.set_title('FoodCourt')\n\n\na=shop['consume_state'].sum()\nb=len(shop['consume_state'])-a\nax3.pie([a,b],labels=['consume','not consume'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax3.set_title('ShoppingMall')\n\na=spa['consume_state'].sum()\nb=len(spa['consume_state'])-a\nax4.pie([a,b],labels=['consume','not consume'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax4.set_title('SPA')\n\na=vr['consume_state'].sum()\nb=len(vr['consume_state'])-a\nax5.pie([a,b],labels=['consume','not consume'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax5.set_title('VR')","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.510854Z","iopub.execute_input":"2022-07-30T15:15:05.511462Z","iopub.status.idle":"2022-07-30T15:15:05.970707Z","shell.execute_reply.started":"2022-07-30T15:15:05.511422Z","shell.execute_reply":"2022-07-30T15:15:05.969540Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The proportions of passengers who choose to spend money on the given luxury amenities was very close.","metadata":{}},{"cell_type":"code","source":"df=pd.concat([Room,Food,shop,spa,vr],axis=1)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.972985Z","iopub.execute_input":"2022-07-30T15:15:05.973342Z","iopub.status.idle":"2022-07-30T15:15:05.981150Z","shell.execute_reply.started":"2022-07-30T15:15:05.973311Z","shell.execute_reply":"2022-07-30T15:15:05.979548Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df['sum']=df.iloc[:,2]+df.iloc[:,5]+df.iloc[:,8]\ndf=df.iloc[:,[0,2,3,5,6,8,9,11,12,13,14,15]]","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:05.983526Z","iopub.execute_input":"2022-07-30T15:15:05.984177Z","iopub.status.idle":"2022-07-30T15:15:06.006388Z","shell.execute_reply.started":"2022-07-30T15:15:05.984130Z","shell.execute_reply":"2022-07-30T15:15:06.005335Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.style.use('ggplot')\nf, (ax1, ax2,ax3,ax4,ax5,ax6) = plt.subplots(1, 6,figsize=(30, 20),dpi=100)\na=df.loc[df['sum']==0,'Transported'].sum()\nb=8693-a\nax1.pie([a,b],labels=['True','False'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax1.set_title('0 amenity')\n\na=df.loc[df['sum']==1,'Transported'].sum()\nb=8693-a\nax2.pie([a,b],labels=['True','False'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax2.set_title('1 amenity')\n\na=df.loc[df['sum']==2,'Transported'].sum()\nb=8693-a\nax3.pie([a,b],labels=['True','False'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax3.set_title('2 amenity')\n\na=df.loc[df['sum']==3,'Transported'].sum()\nb=8693-a\nax4.pie([a,b],labels=['True','False'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax4.set_title('3 amenity')\n\na=df.loc[df['sum']==4,'Transported'].sum()\nb=8693-a\nax5.pie([a,b],labels=['True','False'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax5.set_title('4 amenity')\n\na=df.loc[df['sum']==5,'Transported'].sum()\nb=8693-a\nax6.pie([a,b],labels=['True','False'],colors=['skyblue','salmon'],autopct='%.1f%%')\nax6.set_title('5 amenity')","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:06.007407Z","iopub.execute_input":"2022-07-30T15:15:06.007751Z","iopub.status.idle":"2022-07-30T15:15:06.578563Z","shell.execute_reply.started":"2022-07-30T15:15:06.007719Z","shell.execute_reply":"2022-07-30T15:15:06.577285Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The more amenities a person spent, the less likely he will be sent to another dimension. This may be a important variable, add it to the data set.","metadata":{}},{"cell_type":"code","source":"train=pd.concat([train,df['sum']],axis=1)","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:06.580163Z","iopub.execute_input":"2022-07-30T15:15:06.580510Z","iopub.status.idle":"2022-07-30T15:15:06.592629Z","shell.execute_reply.started":"2022-07-30T15:15:06.580471Z","shell.execute_reply":"2022-07-30T15:15:06.591188Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train","metadata":{"execution":{"iopub.status.busy":"2022-07-30T15:15:06.594513Z","iopub.execute_input":"2022-07-30T15:15:06.595018Z","iopub.status.idle":"2022-07-30T15:15:06.651749Z","shell.execute_reply.started":"2022-07-30T15:15:06.594971Z","shell.execute_reply":"2022-07-30T15:15:06.650883Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Delete the data of those who didn't spend mony on them, to see the price distribution of those amenities.","metadata":{}},{"cell_type":"code","source":"Room1=Room.loc[Room['consume_state']>0,:]\nFood1=Food.loc[Food['consume_state']>0,:]\nshop1=shop.loc[shop['consume_state']>0,:]\nspa1=spa.loc[spa['consume_state']>0,:]\nvr1=vr.loc[vr['consume_state']>0,:]\n\nRoom1=Room1.describe().T\nFood1=Food1.describe().T\nshop1=shop1.describe().T\nspa1=spa1.describe().T\nvr1=vr1.describe().T","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:06.652738Z","iopub.execute_input":"2022-07-30T15:15:06.653052Z","iopub.status.idle":"2022-07-30T15:15:06.716698Z","shell.execute_reply.started":"2022-07-30T15:15:06.653025Z","shell.execute_reply":"2022-07-30T15:15:06.715656Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df=pd.concat([Room1,Food1,shop1,spa1,vr1],)\ndf","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:06.717976Z","iopub.execute_input":"2022-07-30T15:15:06.718496Z","iopub.status.idle":"2022-07-30T15:15:06.749099Z","shell.execute_reply.started":"2022-07-30T15:15:06.718439Z","shell.execute_reply":"2022-07-30T15:15:06.747965Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Here we can see that the distributions of those luxury amenities are not very different, and have very wide range. In the above dataframe, the mean of 'Transported' is equal to the probability that a person will be transported to another dimension, and it's lower than the overall probability.","metadata":{}},{"cell_type":"code","source":"cor=train.corr()\n\nplt.figure(figsize=(10,10))\nsns.heatmap(cor,cmap='coolwarm', vmin=-1, vmax=1, center=0, annot=True, fmt='.2f', \n annot_kws={'fontsize':10})","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2022-07-30T15:15:06.752692Z","iopub.execute_input":"2022-07-30T15:15:06.753057Z","iopub.status.idle":"2022-07-30T15:15:08.738569Z","shell.execute_reply.started":"2022-07-30T15:15:06.753027Z","shell.execute_reply":"2022-07-30T15:15:08.737128Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Variables not significantly correlated, except 'cabin_desk' and 'HomePlanet_Europa'. ","metadata":{}}]}