{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a6971c873507dd68c9ffacc81a815b106c70a6f6"},"cell_type":"code","source":"import os\nimport json\nimport numpy as np\nimport pandas as pd\nfrom pandas.io.json import json_normalize\nimport matplotlib.pyplot as plt\nimport seaborn as sns\ncolor = sns.color_palette()\n\n%matplotlib inline\n\nfrom plotly import tools\nimport plotly.offline as py\npy.init_notebook_mode(connected=True)\nimport plotly.graph_objs as go\n\nfrom sklearn import model_selection, preprocessing, metrics\nimport lightgbm as lgb\n\npd.options.mode.chained_assignment = None\npd.options.display.max_columns = 999","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"962f20b9f96fab06b2f77f2d08267a68d542d67b"},"cell_type":"code","source":"def load_df(csv_path='../input/train.csv', nrows=None):\n    JSON_COLUMNS = ['device', 'geoNetwork', 'totals', 'trafficSource']\n    \n    df = pd.read_csv(csv_path, \n                     converters={column: json.loads for column in JSON_COLUMNS}, \n                     dtype={'fullVisitorId': 'str'}, # Important!!\n                     nrows=nrows)\n    \n    for column in JSON_COLUMNS:\n        column_as_df = json_normalize(df[column])\n        column_as_df.columns = [f\"{column}.{subcolumn}\" for subcolumn in column_as_df.columns]\n        df = df.drop(column, axis=1).merge(column_as_df, right_index=True, left_index=True)\n    print(f\"Loaded {os.path.basename(csv_path)}. Shape: {df.shape}\")\n    return df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b1364a73ec6a4196d5009de0823c0e507329711c"},"cell_type":"code","source":"%%time\ntrain_df = load_df()\ntest_df = load_df(\"../input/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"0e82297ae69479b8b4341120a409b0a8f9259161"},"cell_type":"code","source":"train_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"bc83de9beee3bb476b62daa4b7e968e46865a195"},"cell_type":"code","source":"train_df[\"totals.transactionRevenue\"] = train_df[\"totals.transactionRevenue\"].astype('float')\ngdf = train_df.groupby(\"fullVisitorId\")[\"totals.transactionRevenue\"].sum().reset_index()\n\nplt.figure(figsize=(8,6))\nplt.scatter(range(gdf.shape[0]), np.sort(np.log1p(gdf[\"totals.transactionRevenue\"].values)))\nplt.xlabel('index', fontsize=12)\nplt.ylabel('TransactionRevenue', fontsize=12)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3ae237a247df1bfd7e9b0f6d55f86d84c8fa6627"},"cell_type":"code","source":"nzi = pd.notnull(train_df[\"totals.transactionRevenue\"]).sum()\nnzr = (gdf[\"totals.transactionRevenue\"]>0).sum()\nprint(\"Number of instances in train set with non-zero revenue : \", nzi, \" and ratio is : \", nzi / train_df.shape[0])\nprint(\"Number of unique customers with non-zero revenue : \", nzr, \"and the ratio is : \", nzr / gdf.shape[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ba2c92d81db472ca532534a29208417bdf554c46"},"cell_type":"code","source":"print(\"Number of unique visitors in train set : \",train_df.fullVisitorId.nunique(), \" out of rows : \",train_df.shape[0])\nprint(\"Number of unique visitors in test set : \",test_df.fullVisitorId.nunique(), \" out of rows : \",test_df.shape[0])\nprint(\"Number of common visitors in train and test set : \",len(set(train_df.fullVisitorId.unique()).intersection(set(test_df.fullVisitorId.unique())) ))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"986a0864157e06c491c8498fe11c5e34b49503c3"},"cell_type":"code","source":"const_cols = [c for c in train_df.columns if train_df[c].nunique(dropna=False)==1 ]\nconst_cols","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2de29933e0e1dfa82392e9612db34b68bb4cb4f9"},"cell_type":"code","source":"def horizontal_bar_chart(cnt_srs, color):\n    trace = go.Bar(\n        y=cnt_srs.index[::-1],\n        x=cnt_srs.values[::-1],\n        showlegend=False,\n        orientation = 'h',\n        marker=dict(\n            color=color,\n        ),\n    )\n    return trace\n\n# Device Browser\ncnt_srs = train_df.groupby('device.browser')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", \"mean\"]\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace1 = horizontal_bar_chart(cnt_srs[\"count\"].head(10), 'rgba(50, 171, 96, 0.6)')\ntrace2 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"].head(10), 'rgba(50, 171, 96, 0.6)')\ntrace3 = horizontal_bar_chart(cnt_srs[\"mean\"].head(10), 'rgba(50, 171, 96, 0.6)')\n\n# Device Category\ncnt_srs = train_df.groupby('device.deviceCategory')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", \"mean\"]\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace4 = horizontal_bar_chart(cnt_srs[\"count\"].head(10), 'rgba(71, 58, 131, 0.8)')\ntrace5 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"].head(10), 'rgba(71, 58, 131, 0.8)')\ntrace6 = horizontal_bar_chart(cnt_srs[\"mean\"].head(10), 'rgba(71, 58, 131, 0.8)')\n\n# Operating system\ncnt_srs = train_df.groupby('device.operatingSystem')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", \"mean\"]\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace7 = horizontal_bar_chart(cnt_srs[\"count\"].head(10), 'rgba(246, 78, 139, 0.6)')\ntrace8 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"].head(10),'rgba(246, 78, 139, 0.6)')\ntrace9 = horizontal_bar_chart(cnt_srs[\"mean\"].head(10),'rgba(246, 78, 139, 0.6)')\n\n# Creating two subplots\nfig = tools.make_subplots(rows=3, cols=3, vertical_spacing=0.04, \n                          subplot_titles=[\"Device Browser - Count\", \"Device Browser - Non-zero Revenue Count\", \"Device Browser - Mean Revenue\",\n                                          \"Device Category - Count\",  \"Device Category - Non-zero Revenue Count\", \"Device Category - Mean Revenue\", \n                                          \"Device OS - Count\", \"Device OS - Non-zero Revenue Count\", \"Device OS - Mean Revenue\"])\n\nfig.append_trace(trace1, 1, 1)\nfig.append_trace(trace2, 1, 2)\nfig.append_trace(trace3, 1, 3)\nfig.append_trace(trace4, 2, 1)\nfig.append_trace(trace5, 2, 2)\nfig.append_trace(trace6, 2, 3)\nfig.append_trace(trace7, 3, 1)\nfig.append_trace(trace8, 3, 2)\nfig.append_trace(trace9, 3, 3)\n\nfig['layout'].update(height=1200, width=1200, paper_bgcolor='rgb(233,233,233)', title=\"Device Plots\")\npy.iplot(fig, filename='device-plots')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"4910bfcb73cf3f1150d2af37b3348d93640657c5"},"cell_type":"code","source":"import datetime\n\ndef scatter_plot(cnt_srs, color):\n    trace = go.Scatter(\n        x=cnt_srs.index[::-1],\n        y=cnt_srs.values[::-1],\n        showlegend=False,\n        marker=dict(\n            color=color,\n        ),\n    )\n    return trace\n\ntrain_df['date'] = train_df['date'].apply(lambda x: datetime.date(int(str(x)[:4]), int(str(x)[4:6]), int(str(x)[6:])))\ncnt_srs = train_df.groupby('date')['totals.transactionRevenue'].agg(['size', 'count'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\"]\ncnt_srs = cnt_srs.sort_index()\n#cnt_srs.index = cnt_srs.index.astype('str')\ntrace1 = scatter_plot(cnt_srs[\"count\"], 'red')\ntrace2 = scatter_plot(cnt_srs[\"count of non-zero revenue\"], 'blue')\n\nfig = tools.make_subplots(rows=2, cols=1, vertical_spacing=0.08,\n                          subplot_titles=[\"Date - Count\", \"Date - Non-zero Revenue count\"])\nfig.append_trace(trace1, 1, 1)\nfig.append_trace(trace2, 2, 1)\nfig['layout'].update(height=800, width=800, paper_bgcolor='rgb(233,233,233)', title=\"Date Plots\")\npy.iplot(fig, filename='date-plots')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"5b07a65253974d0a031f5c278b8e4c12b355feb7"},"cell_type":"code","source":"test_df['date'] = test_df['date'].apply(lambda x: datetime.date(int(str(x)[:4]), int(str(x)[4:6]), int(str(x)[6:])))\ncnt_srs = test_df.groupby('date')['fullVisitorId'].size()\n\n\ntrace = scatter_plot(cnt_srs, 'red')\n\nlayout = go.Layout(\n    height=400,\n    width=800,\n    paper_bgcolor='rgb(233,233,233)',\n    title='Dates in Test set'\n)\n\ndata = [trace]\nfig = go.Figure(data=data, layout=layout)\npy.iplot(fig, filename=\"ActivationDate\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"cf3bc27ed0686ef737dd69f21f9b7b73e50589a6"},"cell_type":"code","source":"# Continent\ncnt_srs = train_df.groupby('geoNetwork.continent')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", \"mean\"]\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace1 = horizontal_bar_chart(cnt_srs[\"count\"].head(10), 'rgba(58, 71, 80, 0.6)')\ntrace2 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"].head(10), 'rgba(58, 71, 80, 0.6)')\ntrace3 = horizontal_bar_chart(cnt_srs[\"mean\"].head(10), 'rgba(58, 71, 80, 0.6)')\n\n# Sub-continent\ncnt_srs = train_df.groupby('geoNetwork.subContinent')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", \"mean\"]\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace4 = horizontal_bar_chart(cnt_srs[\"count\"], 'orange')\ntrace5 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"], 'orange')\ntrace6 = horizontal_bar_chart(cnt_srs[\"mean\"], 'orange')\n\n# Network domain\ncnt_srs = train_df.groupby('geoNetwork.networkDomain')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", \"mean\"]\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace7 = horizontal_bar_chart(cnt_srs[\"count\"].head(10), 'blue')\ntrace8 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"].head(10), 'blue')\ntrace9 = horizontal_bar_chart(cnt_srs[\"mean\"].head(10), 'blue')\n\n# Creating two subplots\nfig = tools.make_subplots(rows=3, cols=3, vertical_spacing=0.08, horizontal_spacing=0.15, \n                          subplot_titles=[\"Continent - Count\", \"Continent - Non-zero Revenue Count\", \"Continent - Mean Revenue\",\n                                          \"Sub Continent - Count\",  \"Sub Continent - Non-zero Revenue Count\", \"Sub Continent - Mean Revenue\",\n                                          \"Network Domain - Count\", \"Network Domain - Non-zero Revenue Count\", \"Network Domain - Mean Revenue\"])\n\nfig.append_trace(trace1, 1, 1)\nfig.append_trace(trace2, 1, 2)\nfig.append_trace(trace3, 1, 3)\nfig.append_trace(trace4, 2, 1)\nfig.append_trace(trace5, 2, 2)\nfig.append_trace(trace6, 2, 3)\nfig.append_trace(trace7, 3, 1)\nfig.append_trace(trace8, 3, 2)\nfig.append_trace(trace9, 3, 3)\n\nfig['layout'].update(height=1500, width=1200, paper_bgcolor='rgb(233,233,233)', title=\"Geography Plots\")\npy.iplot(fig, filename='geo-plots')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d5389a2aae0ece369f26e14cef755097c07aa75a"},"cell_type":"code","source":"# Continent\ncnt_srs = train_df.groupby('trafficSource.source')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", \"mean\"]\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace1 = horizontal_bar_chart(cnt_srs[\"count\"].head(10), 'green')\ntrace2 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"].head(10), 'green')\ntrace3 = horizontal_bar_chart(cnt_srs[\"mean\"].head(10), 'green')\n\n# Sub-continent\ncnt_srs = train_df.groupby('trafficSource.medium')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", \"mean\"]\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace4 = horizontal_bar_chart(cnt_srs[\"count\"], 'purple')\ntrace5 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"], 'purple')\ntrace6 = horizontal_bar_chart(cnt_srs[\"mean\"], 'purple')\n\n# Creating two subplots\nfig = tools.make_subplots(rows=2, cols=3, vertical_spacing=0.08, horizontal_spacing=0.15, \n                          subplot_titles=[\"Traffic Source - Count\", \"Traffic Source - Non-zero Revenue Count\", \"Traffic Source - Mean Revenue\",\n                                          \"Traffic Source Medium - Count\",  \"Traffic Source Medium - Non-zero Revenue Count\", \"Traffic Source Medium - Mean Revenue\"\n                                          ])\n\nfig.append_trace(trace1, 1, 1)\nfig.append_trace(trace2, 1, 2)\nfig.append_trace(trace3, 1, 3)\nfig.append_trace(trace4, 2, 1)\nfig.append_trace(trace5, 2, 2)\nfig.append_trace(trace6, 2, 3)\n\nfig['layout'].update(height=1000, width=1200, paper_bgcolor='rgb(233,233,233)', title=\"Traffic Source Plots\")\npy.iplot(fig, filename='traffic-source-plots')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8f9d74aa4e0c20d8ed367355b4ec27d3406600c7"},"cell_type":"code","source":"# Page views\ncnt_srs = train_df.groupby('totals.pageviews')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", \"mean\"]\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace1 = horizontal_bar_chart(cnt_srs[\"count\"].head(60), 'cyan')\ntrace2 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"].head(60), 'cyan')\ntrace5 = horizontal_bar_chart(cnt_srs[\"mean\"].head(60), 'cyan')\n\n# Hits\ncnt_srs = train_df.groupby('totals.hits')['totals.transactionRevenue'].agg(['size', 'count', 'mean'])\ncnt_srs.columns = [\"count\", \"count of non-zero revenue\", 'mean']\ncnt_srs = cnt_srs.sort_values(by=\"count\", ascending=False)\ntrace3 = horizontal_bar_chart(cnt_srs[\"count\"].head(60), 'black')\ntrace4 = horizontal_bar_chart(cnt_srs[\"count of non-zero revenue\"].head(60), 'black')\ntrace6 = horizontal_bar_chart(cnt_srs[\"mean\"].head(60), 'black')\n\n# Creating two subplots\nfig = tools.make_subplots(rows=2, cols=3, vertical_spacing=0.08, horizontal_spacing=0.15, \n                          subplot_titles=[\"Total Pageviews - Count\", \"Total Pageviews - Non-zero Revenue Count\", \"Total Pageviews - Mean Revenue\",\n                                          \"Total Hits - Count\",  \"Total Hits - Non-zero Revenue Count\", \"Total Hits - Mean Revenue\"])\n\nfig.append_trace(trace1, 1, 1)\nfig.append_trace(trace2, 1, 2)\nfig.append_trace(trace5, 1, 3)\nfig.append_trace(trace3, 2, 1)\nfig.append_trace(trace4, 2, 2)\nfig.append_trace(trace6, 2, 3)\n\nfig['layout'].update(height=1200, width=900, paper_bgcolor='rgb(233,233,233)', title=\"Visitor Profile Plots\")\npy.iplot(fig, filename='visitor-profile-plots')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e7dee04d8e3755dda93a739719dfcb6a63b4dbb0"},"cell_type":"code","source":"print(\"Variables not in test but in train : \", set(train_df.columns).difference(set(test_df.columns)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"12a253c474842c3332f9cfe8e01361a5da0f9b59"},"cell_type":"code","source":"cols_to_drop = const_cols + ['sessionId']\n\ntrain_df = train_df.drop(cols_to_drop + [\"trafficSource.campaignCode\"], axis=1)\ntest_df = test_df.drop(cols_to_drop, axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"365422e504d0beab25cd2adb546a770c967d26b0"},"cell_type":"code","source":"# Impute 0 for missing target values\ntrain_df[\"totals.transactionRevenue\"].fillna(0, inplace=True)\ntrain_y = train_df[\"totals.transactionRevenue\"].values\ntrain_id = train_df[\"fullVisitorId\"].values\ntest_id = test_df[\"fullVisitorId\"].values\n\n\n# label encode the categorical variables and convert the numerical variables to float\ncat_cols = [\"channelGrouping\", \"device.browser\", \n            \"device.deviceCategory\", \"device.operatingSystem\", \n            \"geoNetwork.city\", \"geoNetwork.continent\", \n            \"geoNetwork.country\", \"geoNetwork.metro\",\n            \"geoNetwork.networkDomain\", \"geoNetwork.region\", \n            \"geoNetwork.subContinent\", \"trafficSource.adContent\", \n            \"trafficSource.adwordsClickInfo.adNetworkType\", \n            \"trafficSource.adwordsClickInfo.gclId\", \n            \"trafficSource.adwordsClickInfo.page\", \n            \"trafficSource.adwordsClickInfo.slot\", \"trafficSource.campaign\",\n            \"trafficSource.keyword\", \"trafficSource.medium\", \n            \"trafficSource.referralPath\", \"trafficSource.source\",\n            'trafficSource.adwordsClickInfo.isVideoAd', 'trafficSource.isTrueDirect']\nfor col in cat_cols:\n    print(col)\n    lbl = preprocessing.LabelEncoder()\n    lbl.fit(list(train_df[col].values.astype('str')) + list(test_df[col].values.astype('str')))\n    train_df[col] = lbl.transform(list(train_df[col].values.astype('str')))\n    test_df[col] = lbl.transform(list(test_df[col].values.astype('str')))\n\n\nnum_cols = [\"totals.hits\", \"totals.pageviews\", \"visitNumber\", \"visitStartTime\", 'totals.bounces',  'totals.newVisits']    \nfor col in num_cols:\n    train_df[col] = train_df[col].astype(float)\n    test_df[col] = test_df[col].astype(float)\n\n# Split the train dataset into development and valid based on time \ndev_df = train_df[train_df['date']<=datetime.date(2017,5,31)]\nval_df = train_df[train_df['date']>datetime.date(2017,5,31)]\ndev_y = np.log1p(dev_df[\"totals.transactionRevenue\"].values)\nval_y = np.log1p(val_df[\"totals.transactionRevenue\"].values)\n\ndev_X = dev_df[cat_cols + num_cols] \nval_X = val_df[cat_cols + num_cols] \ntest_X = test_df[cat_cols + num_cols] ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a4f5b398e5bf05a5622f0f565dc1494ec0ccd839"},"cell_type":"code","source":"# custom function to run light gbm model\ndef run_lgb(train_X, train_y, val_X, val_y, test_X):\n    params = {\n        \"objective\" : \"regression\",\n        \"metric\" : \"rmse\", \n        \"num_leaves\" : 30,\n        \"min_child_samples\" : 100,\n        \"learning_rate\" : 0.1,\n        \"bagging_fraction\" : 0.7,\n        \"feature_fraction\" : 0.5,\n        \"bagging_frequency\" : 5,\n        \"bagging_seed\" : 2018,\n        \"verbosity\" : -1\n    }\n    \n    lgtrain = lgb.Dataset(train_X, label=train_y)\n    lgval = lgb.Dataset(val_X, label=val_y)\n    model = lgb.train(params, lgtrain, 1000, valid_sets=[lgval], early_stopping_rounds=100, verbose_eval=100)\n    \n    pred_test_y = model.predict(test_X, num_iteration=model.best_iteration)\n    pred_val_y = model.predict(val_X, num_iteration=model.best_iteration)\n    return pred_test_y, model, pred_val_y\n\n# Training the model #\npred_test, model, pred_val = run_lgb(dev_X, dev_y, val_X, val_y, test_X)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b04969ceb5d12c2a89b8467b51090117fdfec923"},"cell_type":"code","source":"from sklearn import metrics\npred_val[pred_val<0] = 0\nval_pred_df = pd.DataFrame({\"fullVisitorId\":val_df[\"fullVisitorId\"].values})\nval_pred_df[\"transactionRevenue\"] = val_df[\"totals.transactionRevenue\"].values\nval_pred_df[\"PredictedRevenue\"] = np.expm1(pred_val)\n#print(np.sqrt(metrics.mean_squared_error(np.log1p(val_pred_df[\"transactionRevenue\"].values), np.log1p(val_pred_df[\"PredictedRevenue\"].values))))\nval_pred_df = val_pred_df.groupby(\"fullVisitorId\")[\"transactionRevenue\", \"PredictedRevenue\"].sum().reset_index()\nprint(np.sqrt(metrics.mean_squared_error(np.log1p(val_pred_df[\"transactionRevenue\"].values), np.log1p(val_pred_df[\"PredictedRevenue\"].values))))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"8b0fc0ef4e3cde1b30691b354400dced87d4155f"},"cell_type":"code","source":"sub_df = pd.DataFrame({\"fullVisitorId\":test_id})\npred_test[pred_test<0] = 0\nsub_df[\"PredictedLogRevenue\"] = np.expm1(pred_test)\nsub_df = sub_df.groupby(\"fullVisitorId\")[\"PredictedLogRevenue\"].sum().reset_index()\nsub_df.columns = [\"fullVisitorId\", \"PredictedLogRevenue\"]\nsub_df[\"PredictedLogRevenue\"] = np.log1p(sub_df[\"PredictedLogRevenue\"])\nsub_df.to_csv(\"baseline_lgb.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"581bcb198db3057ade924b243d0f7f47a4ef012e"},"cell_type":"code","source":"sub_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"44442d793da13db9c3b1e9806ba13b083a91a3ab"},"cell_type":"code","source":"fig, ax = plt.subplots(figsize=(12,18))\nlgb.plot_importance(model, max_num_features=50, height=0.8, ax=ax)\nax.grid(False)\nplt.title(\"LightGBM - Feature Importance\", fontsize=15)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a6e120df3cabd9413077a1dfddb4dc16639502c4"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}