EDA on Datasets
","metadata":{}},{"cell_type":"code","source":"#Load all the datasets\narticles = pd.read_csv(\"../input/h-and-m-personalized-fashion-recommendations/articles.csv\")\ncustomers = pd.read_csv(\"../input/h-and-m-personalized-fashion-recommendations/customers.csv\")\ntransactions = pd.read_csv(\"../input/h-and-m-personalized-fashion-recommendations/transactions_train.csv\")","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:02:22.852751Z","iopub.execute_input":"2022-03-19T09:02:22.853391Z","iopub.status.idle":"2022-03-19T09:03:29.481198Z","shell.execute_reply.started":"2022-03-19T09:02:22.853352Z","shell.execute_reply":"2022-03-19T09:03:29.480450Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Let's find out the shapes of all three dataframes\nshape=pd.DataFrame({\"Total Rows\":[articles.shape[0],customers.shape[0],transactions.shape[0]],\n \"Total Columns\":[articles.shape[1],customers.shape[1],transactions.shape[1]]},index=['articles','customers','transactions'])\nshape","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:03:49.829298Z","iopub.execute_input":"2022-03-19T09:03:49.829568Z","iopub.status.idle":"2022-03-19T09:03:49.847836Z","shell.execute_reply.started":"2022-03-19T09:03:49.829539Z","shell.execute_reply":"2022-03-19T09:03:49.847222Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"n = len(pd.unique(transactions['customer_id'])) \nm = len(pd.unique(customers['customer_id'])) \nlength=len(set(transactions.customer_id.values.tolist()))/customers.shape[0]\nnpur=100-(length*100)\nprint(\"Total No of customers:\",m)\nprint(\"No of customers who made at least one transaction:\",n)\nprint(\"% of customers who made a at least one transaction : \",length*100)\nprint(\"Number of customers who did not make a purchase : \",(customers.shape[0] - len(set(transactions.customer_id.values.tolist()))))\nprint(\"% of customers who did not make a purchase : \",npur)\nprint(\"It seems that not all customers made a purchase, there is around 1% with no purchase history.\")","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:03:59.251893Z","iopub.execute_input":"2022-03-19T09:03:59.252723Z","iopub.status.idle":"2022-03-19T09:04:14.121035Z","shell.execute_reply.started":"2022-03-19T09:03:59.252686Z","shell.execute_reply":"2022-03-19T09:04:14.120173Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"transactions.head()","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:04:31.792277Z","iopub.execute_input":"2022-03-19T09:04:31.792894Z","iopub.status.idle":"2022-03-19T09:04:31.804016Z","shell.execute_reply.started":"2022-03-19T09:04:31.792856Z","shell.execute_reply":"2022-03-19T09:04:31.803427Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"customers.head()","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:04:39.595580Z","iopub.execute_input":"2022-03-19T09:04:39.595880Z","iopub.status.idle":"2022-03-19T09:04:39.609145Z","shell.execute_reply.started":"2022-03-19T09:04:39.595850Z","shell.execute_reply":"2022-03-19T09:04:39.608643Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"articles.head()","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:04:46.077645Z","iopub.execute_input":"2022-03-19T09:04:46.078218Z","iopub.status.idle":"2022-03-19T09:04:46.109037Z","shell.execute_reply.started":"2022-03-19T09:04:46.078173Z","shell.execute_reply":"2022-03-19T09:04:46.108052Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#check null values in transaction dataset\ntransactions.isna().sum()","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:04:53.635214Z","iopub.execute_input":"2022-03-19T09:04:53.635488Z","iopub.status.idle":"2022-03-19T09:04:56.412925Z","shell.execute_reply.started":"2022-03-19T09:04:53.635460Z","shell.execute_reply":"2022-03-19T09:04:56.412057Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Articles Sold
","metadata":{}},{"cell_type":"code","source":"year=transactions.groupby('t_dat').count()[['article_id']]\nyearwise1=year.reset_index()\n#yearwise1.head()\nprint (transactions.t_dat.min())\nprint (transactions.t_dat.max())","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:05:56.563030Z","iopub.execute_input":"2022-03-19T09:05:56.564663Z","iopub.status.idle":"2022-03-19T09:06:05.905840Z","shell.execute_reply.started":"2022-03-19T09:05:56.564572Z","shell.execute_reply":"2022-03-19T09:06:05.904931Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"yearasecact = yearwise1.sort_values(['article_id'], ascending=False).head(5)\nyearasecact","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:06:09.337477Z","iopub.execute_input":"2022-03-19T09:06:09.337971Z","iopub.status.idle":"2022-03-19T09:06:09.349616Z","shell.execute_reply.started":"2022-03-19T09:06:09.337943Z","shell.execute_reply":"2022-03-19T09:06:09.348839Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"yearwise1['t_dat'] = pd.to_datetime(yearwise1['t_dat'], format='%Y/%m/%d')\n\nsns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,12)\n\nax.plot('t_dat', 'article_id', data=yearwise1, color='#6a0573', linewidth=2)\n\nplt.tight_layout()\nax.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m'))\nax.xaxis.set_major_locator(ticker.MultipleLocator(100))\nplt.xticks(rotation=90)\nttl = ax.set_title('Articles Sold from 2018-09-20 to 2020-09-22', fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\n\nx_line_annotation = dt.datetime(2019,9,22)\n\nax.annotate('Maximum Articles Sold',\n xy=(x_line_annotation, 198522),\n xycoords='data',\n xytext=(55, 0), textcoords='offset points',\n size=15, va=\"center\",\n color='#3e0542',\n bbox=dict(boxstyle=\"round\",facecolor='#f7daf7', edgecolor='#3e0542'),\n arrowprops=dict(arrowstyle=\"wedge,tail_width=1.\",\n facecolor='#f7daf7', \n edgecolor='#3e0542',\n relpos=(0.1, 0.4)))\n\n\nttl.set_position([.5, 1.02])\nax.set_ylabel('No of Articles', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\nfor label in (ax.get_xticklabels() + ax.get_yticklabels()):\n label.set_fontsize(14)\n# Adjust subplots so that the title and labels would fit\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:07:23.477373Z","iopub.execute_input":"2022-03-19T09:07:23.477736Z","iopub.status.idle":"2022-03-19T09:07:23.958789Z","shell.execute_reply.started":"2022-03-19T09:07:23.477700Z","shell.execute_reply":"2022-03-19T09:07:23.957994Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As shown in the graph we see that there are distinct spikes in 3 years.Maximum articles 198,622 are sold on the date 2019-09-28 which breaks all the records in 3 years.where as second maximum 162,799 articles are sold on date 2020-04-11 and third maximum 160,875 articles are sold on date 2019-11-29.","metadata":{}},{"cell_type":"markdown","source":"#Transaction Amount
","metadata":{}},{"cell_type":"code","source":"yearp=transactions.groupby('t_dat').sum()[['price']]\nyearwise1p=yearp.reset_index()\n#yearwise1p.head()\nprint (yearwise1p.price.max())","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:07:37.938624Z","iopub.execute_input":"2022-03-19T09:07:37.938889Z","iopub.status.idle":"2022-03-19T09:07:41.781953Z","shell.execute_reply.started":"2022-03-19T09:07:37.938862Z","shell.execute_reply":"2022-03-19T09:07:41.780915Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"yearasec = yearwise1p.sort_values(['price'], ascending=False).head(5)\nyearasec","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:07:44.410390Z","iopub.execute_input":"2022-03-19T09:07:44.411236Z","iopub.status.idle":"2022-03-19T09:07:44.425617Z","shell.execute_reply.started":"2022-03-19T09:07:44.411201Z","shell.execute_reply":"2022-03-19T09:07:44.425050Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"yearwise1p['t_dat'] = pd.to_datetime(yearwise1p['t_dat'], format='%Y/%m/%d')\n\nsns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,12)\n\nax.plot('t_dat', 'price', data=yearwise1p, color='#6a0573', linewidth=2)\n\nplt.tight_layout()\nax.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m'))\nax.xaxis.set_major_locator(ticker.MultipleLocator(100))\nplt.xticks(rotation=90)\nttl = ax.set_title('Transaction amount from 2018-09-20 to 2020-09-22', fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\nx_line_annotation = dt.datetime(2019,9,22)\n\nax.annotate('Maximum Amount Transaction',\n xy=(x_line_annotation,6161),\n xycoords='data',\n xytext=(55, 0), textcoords='offset points',\n size=15, va=\"center\",\n color='#3e0542',\n bbox=dict(boxstyle=\"round\",facecolor='#f7daf7', edgecolor='#3e0542'),\n arrowprops=dict(arrowstyle=\"wedge,tail_width=1.\",\n facecolor='#f7daf7', \n edgecolor='#3e0542',\n relpos=(0.1, 0.4)))\n\nttl.set_position([.5, 1.02])\nax.set_ylabel('Amount', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\nfor label in (ax.get_xticklabels() + ax.get_yticklabels()):\n label.set_fontsize(14)\n# Adjust subplots so that the title and labels would fit\n\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:07:52.405804Z","iopub.execute_input":"2022-03-19T09:07:52.406343Z","iopub.status.idle":"2022-03-19T09:07:52.917858Z","shell.execute_reply.started":"2022-03-19T09:07:52.406309Z","shell.execute_reply":"2022-03-19T09:07:52.916906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We see that the maximum transaction amount on date 2019-09-28 is 6,161.where as second maximum transaction is 4,444 on date 2019-11-29 which shows that the transacation amount is 25% decreases in 2019-11-29.","metadata":{}},{"cell_type":"markdown","source":"#Top Ten Customers
","metadata":{}},{"cell_type":"code","source":"check=transactions.groupby('customer_id').count()[['article_id']].sort_values('article_id', ascending=False)\nnewcheck=check.head(10)\nnewcheck1=newcheck.reset_index()","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:10:04.360827Z","iopub.execute_input":"2022-03-19T09:10:04.361310Z","iopub.status.idle":"2022-03-19T09:10:17.607645Z","shell.execute_reply.started":"2022-03-19T09:10:04.361271Z","shell.execute_reply":"2022-03-19T09:10:17.607033Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig = go.Figure(data=[go.Table(\n header=dict(values = [['Customer IDArticles Sold by Age Distribution
","metadata":{}},{"cell_type":"code","source":"custfin= pd.DataFrame(customers, columns = ['customer_id','age'])","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:11:06.529539Z","iopub.execute_input":"2022-03-19T09:11:06.529855Z","iopub.status.idle":"2022-03-19T09:11:06.590997Z","shell.execute_reply.started":"2022-03-19T09:11:06.529816Z","shell.execute_reply":"2022-03-19T09:11:06.590362Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"total_tran = pd.merge(custfin,transactions, how='right', on='customer_id')","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:11:09.043970Z","iopub.execute_input":"2022-03-19T09:11:09.044257Z","iopub.status.idle":"2022-03-19T09:11:26.447031Z","shell.execute_reply.started":"2022-03-19T09:11:09.044223Z","shell.execute_reply":"2022-03-19T09:11:26.446057Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"total_tran[\"age\"].fillna(value=0,inplace=True)\ntotal_tran[\"age\"]=total_tran[\"age\"].apply(int)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:11:48.223801Z","iopub.execute_input":"2022-03-19T09:11:48.224080Z","iopub.status.idle":"2022-03-19T09:11:59.139241Z","shell.execute_reply.started":"2022-03-19T09:11:48.224048Z","shell.execute_reply":"2022-03-19T09:11:59.138347Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,12)\nax = sns.histplot(data=total_tran, x='age', bins=50,color='#6a0573')\n\nax.annotate('Age \\n not given',\n xy=(0,216100),\n xycoords='data',\n xytext=(55, 0), textcoords='offset points',\n size=10, va=\"center\",\n color='#3e0542',\n bbox=dict(boxstyle=\"round\",facecolor='#f7daf7', edgecolor='#3e0542'),\n arrowprops=dict(arrowstyle=\"wedge,tail_width=1.\",\n facecolor='#f7daf7', \n edgecolor='#3e0542',\n relpos=(0.1, 0.4)))\n\nax.axvline(x=20, linestyle='dashed', alpha=0.5,color='#3e0542')\nax.axvline(x=38, linestyle='dashed', alpha=0.5,color='#3e0542')\nax.text(x=20.5, y=3161000, s='Maximum buyers range', alpha=0.7, color='#3e0542',fontweight = 'bold')\nttl.set_position([.5, 1.02])\nax.set_ylabel('No of Articles', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nax.set_xlabel('Age', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\nfor label in (ax.get_xticklabels() + ax.get_yticklabels()):\n label.set_fontsize(14)\nttl = ax.set_title('Articles sold by Age', fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\n\n# Adjust subplots so that the title and labels would fit\n\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:12:02.618974Z","iopub.execute_input":"2022-03-19T09:12:02.619719Z","iopub.status.idle":"2022-03-19T09:12:10.529230Z","shell.execute_reply.started":"2022-03-19T09:12:02.619676Z","shell.execute_reply":"2022-03-19T09:12:10.528239Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The distribution shows that the maximum buyer range is from 21 to 39 years.Few customers age are not given.","metadata":{}},{"cell_type":"markdown","source":"#Articles Sold by Sales Channel
","metadata":{}},{"cell_type":"code","source":"datanew= pd.DataFrame(total_tran, columns = ['price','t_dat','sales_channel_id','article_id'])\ndf = datanew.groupby([\"t_dat\", \"sales_channel_id\"])[\"article_id\"].count().reset_index()\nprint (df.article_id.max())\nprint (df.article_id.min())","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:12:30.826193Z","iopub.execute_input":"2022-03-19T09:12:30.827083Z","iopub.status.idle":"2022-03-19T09:12:38.667335Z","shell.execute_reply.started":"2022-03-19T09:12:30.827031Z","shell.execute_reply":"2022-03-19T09:12:38.666386Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dfasec = df.sort_values(['article_id'], ascending=True).head(5)\ndfasec","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:12:44.397601Z","iopub.execute_input":"2022-03-19T09:12:44.398059Z","iopub.status.idle":"2022-03-19T09:12:44.406694Z","shell.execute_reply.started":"2022-03-19T09:12:44.398015Z","shell.execute_reply":"2022-03-19T09:12:44.406200Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df['t_dat'] = pd.to_datetime(df['t_dat'], format='%Y/%m/%d')","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:12:51.064291Z","iopub.execute_input":"2022-03-19T09:12:51.064577Z","iopub.status.idle":"2022-03-19T09:12:51.072218Z","shell.execute_reply.started":"2022-03-19T09:12:51.064532Z","shell.execute_reply":"2022-03-19T09:12:51.071564Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"xmin = df[\"t_dat\"].min()\nxmax = df[\"t_dat\"].max()\n\nymin = df[\"article_id\"].min() - 1000\nymax = df[\"article_id\"].max() + 1000","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:12:53.248247Z","iopub.execute_input":"2022-03-19T09:12:53.248802Z","iopub.status.idle":"2022-03-19T09:12:53.254710Z","shell.execute_reply.started":"2022-03-19T09:12:53.248766Z","shell.execute_reply":"2022-03-19T09:12:53.253879Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#df['t_dat'] = pd.to_datetime(df['t_dat'], format='%Y/%m/%d')\nsns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,12)\n\nax.plot(df.loc[df[\"sales_channel_id\"]==1, \"t_dat\"], df.loc[df[\"sales_channel_id\"]==1, \"article_id\"], label=\"Sales Channel 1\", color=\"Darkblue\")\nax.plot(df.loc[df[\"sales_channel_id\"]==2, \"t_dat\"], df.loc[df[\"sales_channel_id\"]==2, \"article_id\"], label=\"Sales Channel 2\", color=\"Magenta\")\nax.annotate('Maximum Items Sold',\n xy=(x_line_annotation,167500),\n xycoords='data',\n xytext=(55, 0), textcoords='offset points',\n size=15, va=\"center\",\n color='#3e0542',\n bbox=dict(boxstyle=\"round\",facecolor='#f7daf7', edgecolor='#3e0542'),\n arrowprops=dict(arrowstyle=\"wedge,tail_width=1.\",\n facecolor='#f7daf7', \n edgecolor='#3e0542',\n relpos=(0.1, 0.4)))\nax.set_ylim(ymin, ymax)\nax.set_xlim(xmin, xmax)\n\nax.fill_betweenx([ymin,ymax],18343, 18384, color=\"gray\", alpha=0.3)\n\nprops = dict(boxstyle='round',facecolor='#f7daf7', edgecolor='#3e0542', alpha=0.5)\nax.annotate(\"Missing transaction\\n period\", (18342, 17000), (18270, 67000), \\\n arrowprops={\"arrowstyle\": \"->\", \"color\":\"C1\"},\n color='#3e0542',\n bbox=props,\n fontproperties='italic'\n );\n\n\nax.set_ylabel('No of Articles', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\n\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\nplt.xticks(rotation=90)\nlegend=plt.legend(title=\"Sales Channel ID\",labelcolor='linecolor')\nplt.setp(legend.get_title(), color='#3e0542',fontweight = 'bold')\nfor label in (ax.get_xticklabels() + ax.get_yticklabels()):\n label.set_fontsize(14)\nplt.title(f\"Articles sold by Sales Channel\",fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:12:59.475821Z","iopub.execute_input":"2022-03-19T09:12:59.476878Z","iopub.status.idle":"2022-03-19T09:13:00.073195Z","shell.execute_reply.started":"2022-03-19T09:12:59.476837Z","shell.execute_reply":"2022-03-19T09:13:00.072369Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"There are two sales channel 1 and 2.Sales channel 2 has the highest sold record as compared to sales channel 1.Transactions are also missing for sales channel 1 for few months.","metadata":{}},{"cell_type":"markdown","source":"#Transaction Amount by Sales Channel
","metadata":{}},{"cell_type":"code","source":"dfp = datanew.groupby([\"t_dat\", \"sales_channel_id\"])[\"price\"].sum().reset_index()\nprint (dfp.price.max())","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:13:39.283949Z","iopub.execute_input":"2022-03-19T09:13:39.284612Z","iopub.status.idle":"2022-03-19T09:13:43.032118Z","shell.execute_reply.started":"2022-03-19T09:13:39.284560Z","shell.execute_reply":"2022-03-19T09:13:43.031229Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dfp['t_dat'] = pd.to_datetime(dfp['t_dat'], format='%Y/%m/%d')\nsns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,12)\n\nax.plot(dfp.loc[dfp[\"sales_channel_id\"]==1, \"t_dat\"], dfp.loc[dfp[\"sales_channel_id\"]==1, \"price\"], label=\"Sales Channel 1\", color=\"Darkblue\")\nax.plot(dfp.loc[dfp[\"sales_channel_id\"]==2, \"t_dat\"], dfp.loc[dfp[\"sales_channel_id\"]==2, \"price\"], label=\"Sales Channel 2\", color=\"Magenta\")\nax.annotate('Maximum amount',\n xy=(x_line_annotation,5365),\n xycoords='data',\n xytext=(55, 0), textcoords='offset points',\n size=15, va=\"center\",\n color='#3e0542',\n bbox=dict(boxstyle=\"round\",facecolor='#f7daf7', edgecolor='#3e0542'),\n arrowprops=dict(arrowstyle=\"wedge,tail_width=1.\",\n facecolor='#f7daf7', \n edgecolor='#3e0542',\n relpos=(0.1, 0.4)))\n\n\nax.set_ylabel('Amount', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\n\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\nplt.xticks(rotation=90)\nlegend=plt.legend(title=\"Sales Channel ID\",labelcolor='linecolor')\nplt.setp(legend.get_title(), color='#3e0542',fontweight = 'bold')\nfor label in (ax.get_xticklabels() + ax.get_yticklabels()):\n label.set_fontsize(14)\nplt.title(f\"Transactions Amount by Sales Channel\",fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:13:45.617588Z","iopub.execute_input":"2022-03-19T09:13:45.618493Z","iopub.status.idle":"2022-03-19T09:13:46.106783Z","shell.execute_reply.started":"2022-03-19T09:13:45.618453Z","shell.execute_reply":"2022-03-19T09:13:46.106014Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Sales channel 2 has the highest transaction amount in 3 years.Maximum transaction amount on the date 2019-09-28 are also hit by sales channel 2.Transactions amount are missing for sales channel 1 for few months.","metadata":{}},{"cell_type":"markdown","source":"#Articles sold by Product Group
","metadata":{}},{"cell_type":"code","source":"datanew1= pd.DataFrame(transactions, columns = ['article_id','price'])\nartdept=pd.DataFrame(articles, columns = ['article_id','colour_group_name','department_name','index_group_name','product_group_name'])\n","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:14:31.844836Z","iopub.execute_input":"2022-03-19T09:14:31.845118Z","iopub.status.idle":"2022-03-19T09:14:32.061507Z","shell.execute_reply.started":"2022-03-19T09:14:31.845075Z","shell.execute_reply":"2022-03-19T09:14:32.060477Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"department = pd.merge(artdept,datanew1, how='right', on='article_id')","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:14:34.463206Z","iopub.execute_input":"2022-03-19T09:14:34.463814Z","iopub.status.idle":"2022-03-19T09:14:40.418743Z","shell.execute_reply.started":"2022-03-19T09:14:34.463780Z","shell.execute_reply":"2022-03-19T09:14:40.417895Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"departmentc=department.groupby(['product_group_name','index_group_name'])['article_id'].count().reset_index()\ndepartmentc1 = departmentc.sort_values(['article_id'], ascending=False)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:14:43.954426Z","iopub.execute_input":"2022-03-19T09:14:43.954870Z","iopub.status.idle":"2022-03-19T09:14:50.350943Z","shell.execute_reply.started":"2022-03-19T09:14:43.954832Z","shell.execute_reply":"2022-03-19T09:14:50.350229Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,16)\nflatui = [\"#9b59b6\", \"#3498db\", \"#e74c3c\", \"#34495e\", \"#2ecc71\"]\n\nsns.barplot(data=departmentc1,y=\"product_group_name\", x=\"article_id\",hue=\"index_group_name\",palette=flatui,alpha = 0.6, edgecolor = 'k', linewidth = 2)\n\nplt.tight_layout()\n\n\nttl = ax.set_title('Articles Sold by Product Group', fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\n\n\nttl.set_position([.5, 1.02])\nax.set_ylabel('Product Group', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nax.set_xlabel('No of Articles', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\nlegend=plt.legend(title=\"Index Group Name\")\nplt.setp(legend.get_title(),fontweight = 'bold')\nfor label in (ax.get_xticklabels() + ax.get_yticklabels()):\n label.set_fontsize(14)\n# Adjust subplots so that the title and labels would fit\n\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:14:52.120595Z","iopub.execute_input":"2022-03-19T09:14:52.120880Z","iopub.status.idle":"2022-03-19T09:14:53.464797Z","shell.execute_reply.started":"2022-03-19T09:14:52.120847Z","shell.execute_reply":"2022-03-19T09:14:53.463894Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As shown in the chart Ladieswear index group are more dominant for top 5 product group.However the second index group is divided.","metadata":{}},{"cell_type":"markdown","source":"#Articles Sold by Department
","metadata":{}},{"cell_type":"code","source":"departmentp=department.groupby(['department_name'])['article_id'].count().reset_index()\ndepartmentp1 = departmentp.sort_values(['article_id'], ascending=False).head(50)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:15:12.288626Z","iopub.execute_input":"2022-03-19T09:15:12.289146Z","iopub.status.idle":"2022-03-19T09:15:15.396620Z","shell.execute_reply.started":"2022-03-19T09:15:12.289103Z","shell.execute_reply":"2022-03-19T09:15:15.395726Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,16)\nsns.barplot(data=departmentp1,y=\"department_name\", x=\"article_id\",palette=\"flare\",alpha = 0.6, edgecolor = 'k', linewidth = 2)\nplt.tight_layout()\nttl = ax.set_title('Articles Sold by Department', fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\nttl.set_position([.5, 1.02])\nax.set_ylabel('Department Name', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nax.set_xlabel('No of Articles', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\n\nfor label in (ax.get_xticklabels() + ax.get_yticklabels()):\n label.set_fontsize(14)\n# Adjust subplots so that the title and labels would fit\n\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:15:17.321613Z","iopub.execute_input":"2022-03-19T09:15:17.322233Z","iopub.status.idle":"2022-03-19T09:15:18.503138Z","shell.execute_reply.started":"2022-03-19T09:15:17.322198Z","shell.execute_reply":"2022-03-19T09:15:18.502331Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As shown in chart the articles swimwear,trouser and blouse are the most dominant.","metadata":{}},{"cell_type":"markdown","source":"#Articles Sold by Colour
","metadata":{}},{"cell_type":"code","source":"art1=pd.DataFrame(articles, columns = ['article_id','colour_group_name','garment_group_name','section_name','product_type_name'])\n","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:15:30.398900Z","iopub.execute_input":"2022-03-19T09:15:30.399770Z","iopub.status.idle":"2022-03-19T09:15:30.413542Z","shell.execute_reply.started":"2022-03-19T09:15:30.399731Z","shell.execute_reply":"2022-03-19T09:15:30.412595Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dep1 = pd.merge(art1,datanew1, how='right', on='article_id')","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:15:33.587291Z","iopub.execute_input":"2022-03-19T09:15:33.587592Z","iopub.status.idle":"2022-03-19T09:15:43.369982Z","shell.execute_reply.started":"2022-03-19T09:15:33.587562Z","shell.execute_reply":"2022-03-19T09:15:43.369065Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dep2=dep1.groupby(['colour_group_name'])['article_id'].count().reset_index()\ndepa = dep2.sort_values(['article_id'], ascending=False)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:15:46.324732Z","iopub.execute_input":"2022-03-19T09:15:46.325592Z","iopub.status.idle":"2022-03-19T09:15:49.438676Z","shell.execute_reply.started":"2022-03-19T09:15:46.325545Z","shell.execute_reply":"2022-03-19T09:15:49.437839Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,16)\nsns.barplot(data=depa,y=\"colour_group_name\", x=\"article_id\",palette=\"flare\",alpha = 0.6, edgecolor = 'k', linewidth = 2)\nplt.tight_layout()\nttl = ax.set_title('Articles Sold by Colour', fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\nttl.set_position([.5, 1.02])\nax.set_ylabel('Colour Group', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nax.set_xlabel('No of Articles', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\n\nfor label in (ax.get_xticklabels() + ax.get_yticklabels()):\n label.set_fontsize(14)\n# Adjust subplots so that the title and labels would fit\n\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:15:56.551481Z","iopub.execute_input":"2022-03-19T09:15:56.552114Z","iopub.status.idle":"2022-03-19T09:15:57.684464Z","shell.execute_reply.started":"2022-03-19T09:15:56.552071Z","shell.execute_reply":"2022-03-19T09:15:57.683690Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Black color garments are highly demanded by the customers.","metadata":{}},{"cell_type":"markdown","source":"#Articles Sold by Garment
","metadata":{}},{"cell_type":"code","source":"dep3=dep1.groupby(['garment_group_name'])['article_id'].count().reset_index()\ndepa1 = dep3.sort_values(['article_id'], ascending=False)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:16:07.633842Z","iopub.execute_input":"2022-03-19T09:16:07.636281Z","iopub.status.idle":"2022-03-19T09:16:10.616232Z","shell.execute_reply.started":"2022-03-19T09:16:07.636235Z","shell.execute_reply":"2022-03-19T09:16:10.615370Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,16)\nplt.hlines(data=depa1,y=\"garment_group_name\",xmin=0,xmax=\"article_id\",alpha = 0.6, edgecolor = 'k', linewidth = 2,color='#3e0542')\nplt.plot(depa1['article_id'], depa1['garment_group_name'], \"D\")\n \nplt.tight_layout()\nttl = ax.set_title('Articles Sold by Garment', fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\nttl.set_position([.5, 1.02])\nax.set_ylabel('Grament Group', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nax.set_xlabel('No of Articles', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\n\nfor label in (ax.get_xticklabels() + ax.get_yticklabels()):\n label.set_fontsize(14)\n# Adjust subplots so that the title and labels would fit\n\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:16:13.200362Z","iopub.execute_input":"2022-03-19T09:16:13.200652Z","iopub.status.idle":"2022-03-19T09:16:13.671607Z","shell.execute_reply.started":"2022-03-19T09:16:13.200622Z","shell.execute_reply":"2022-03-19T09:16:13.670834Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Jersey fancy and basic are the most frequent garment for customers.","metadata":{}},{"cell_type":"markdown","source":"#Fashion News Frequency
","metadata":{}},{"cell_type":"code","source":"cus=pd.DataFrame(customers, columns = ['club_member_status','fashion_news_frequency','customer_id'])\ntrans= pd.DataFrame(transactions, columns = ['customer_id'])","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:16:23.559950Z","iopub.execute_input":"2022-03-19T09:16:23.560815Z","iopub.status.idle":"2022-03-19T09:16:24.021587Z","shell.execute_reply.started":"2022-03-19T09:16:23.560776Z","shell.execute_reply":"2022-03-19T09:16:24.020664Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"custran = pd.merge(cus,trans, how='right', on='customer_id')","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:16:31.064860Z","iopub.execute_input":"2022-03-19T09:16:31.065382Z","iopub.status.idle":"2022-03-19T09:16:43.567499Z","shell.execute_reply.started":"2022-03-19T09:16:31.065340Z","shell.execute_reply":"2022-03-19T09:16:43.566790Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ct1=custran.groupby(['fashion_news_frequency'])['customer_id'].count().reset_index()\nct2 = ct1.sort_values(['customer_id'], ascending=False)\n#ct2.head()","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:16:49.752489Z","iopub.execute_input":"2022-03-19T09:16:49.752736Z","iopub.status.idle":"2022-03-19T09:16:54.463004Z","shell.execute_reply.started":"2022-03-19T09:16:49.752709Z","shell.execute_reply":"2022-03-19T09:16:54.462202Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,8)\nsns.barplot(data=ct2,x=\"fashion_news_frequency\", y=\"customer_id\",palette=\"flare\",alpha = 0.6, edgecolor = 'k', linewidth = 2)\nttl = ax.set_title('Fashion News Frequency', fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\nttl.set_position([.5, 1.02])\nax.set_ylabel('No of Cutomers', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nax.set_xlabel('Fashion News Frequency', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\n#for label in (ax.get_xticklabels() + ax.get_yticklabels()):\n #label.set_fontsize(14)\n# Adjust subplots so that the title and labels would fit\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:16:57.258067Z","iopub.execute_input":"2022-03-19T09:16:57.258380Z","iopub.status.idle":"2022-03-19T09:16:57.511331Z","shell.execute_reply.started":"2022-03-19T09:16:57.258348Z","shell.execute_reply":"2022-03-19T09:16:57.510525Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We see that most of the customers do not recieve ang regular update about fashion news.","metadata":{}},{"cell_type":"markdown","source":"#Club Member Status
","metadata":{}},{"cell_type":"code","source":"cms1=custran.groupby(['club_member_status'])['customer_id'].count().reset_index()\ncms2 = cms1.sort_values(['customer_id'], ascending=False)\n#cms2.head()","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:17:07.020986Z","iopub.execute_input":"2022-03-19T09:17:07.021673Z","iopub.status.idle":"2022-03-19T09:17:11.728031Z","shell.execute_reply.started":"2022-03-19T09:17:07.021631Z","shell.execute_reply":"2022-03-19T09:17:11.727310Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(facecolor='#d6b6d5')\nfig.set_size_inches(18,8)\nsns.barplot(data=cms2,x=\"club_member_status\", y=\"customer_id\",palette=\"flare\",alpha = 0.6, edgecolor = 'k', linewidth = 2)\nttl = ax.set_title('Club Member Status', fontsize=18, pad=18, color=font_color, **csfont,fontweight = 'bold')\nttl.set_position([.5, 1.02])\nax.set_ylabel('No of Cutomers', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nax.set_xlabel('Club Member Status', color=font_color, fontsize=16, **hfont,fontweight = 'bold')\nplt.xticks(color=font_color, **hfont,fontweight = 'bold')\nplt.yticks(color=font_color, **hfont,fontweight = 'bold')\n#for label in (ax.get_xticklabels() + ax.get_yticklabels()):\n #label.set_fontsize(14)\n# Adjust subplots so that the title and labels would fit\nplt.subplots_adjust(top=0.85, bottom=0.3, left=0.1, right=0.9)","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:17:13.742298Z","iopub.execute_input":"2022-03-19T09:17:13.742589Z","iopub.status.idle":"2022-03-19T09:17:13.975682Z","shell.execute_reply.started":"2022-03-19T09:17:13.742553Z","shell.execute_reply":"2022-03-19T09:17:13.974826Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Most of the customers have an active membership status,only few are in pre-create status and no one with left club status.","metadata":{}},{"cell_type":"markdown","source":"#Word Cloud for Description
","metadata":{}},{"cell_type":"code","source":"prod_desc = articles[articles.detail_desc.notnull()].detail_desc.sample(5000).values","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:17:24.720475Z","iopub.execute_input":"2022-03-19T09:17:24.721145Z","iopub.status.idle":"2022-03-19T09:17:24.751507Z","shell.execute_reply.started":"2022-03-19T09:17:24.721103Z","shell.execute_reply":"2022-03-19T09:17:24.750547Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from wordcloud import WordCloud, STOPWORDS\n\nstopwords = set(STOPWORDS) \nwordcloud = WordCloud(width = 800, \n height = 800,\n background_color ='white',\n min_font_size = 10,\n stopwords = stopwords,).generate(' '.join(prod_desc)) \n\n# plot the WordCloud image \nplt.figure(figsize = (8, 8), facecolor = '#d6b6d5') \nplt.imshow(wordcloud) \nplt.axis(\"off\") \nplt.tight_layout(pad = 0) \n\nplt.show() ","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:17:27.763741Z","iopub.execute_input":"2022-03-19T09:17:27.764025Z","iopub.status.idle":"2022-03-19T09:17:30.117697Z","shell.execute_reply.started":"2022-03-19T09:17:27.763992Z","shell.execute_reply":"2022-03-19T09:17:30.116890Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Mean Price for Articles
","metadata":{}},{"cell_type":"code","source":"articles_for_merge = articles[['article_id', 'product_group_name']]","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:17:39.783734Z","iopub.execute_input":"2022-03-19T09:17:39.784363Z","iopub.status.idle":"2022-03-19T09:17:39.790534Z","shell.execute_reply.started":"2022-03-19T09:17:39.784323Z","shell.execute_reply":"2022-03-19T09:17:39.789694Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"articles_for_merge = transactions[['article_id', 'price', 't_dat']].merge(articles_for_merge, on='article_id', how='left')","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:17:45.135816Z","iopub.execute_input":"2022-03-19T09:17:45.136093Z","iopub.status.idle":"2022-03-19T09:17:54.279777Z","shell.execute_reply.started":"2022-03-19T09:17:45.136062Z","shell.execute_reply":"2022-03-19T09:17:54.278598Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"articles_for_merge['t_dat'] = pd.to_datetime(articles_for_merge['t_dat'], format='%Y/%m/%d')","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:17:59.884569Z","iopub.execute_input":"2022-03-19T09:17:59.885221Z","iopub.status.idle":"2022-03-19T09:18:03.706847Z","shell.execute_reply.started":"2022-03-19T09:17:59.885178Z","shell.execute_reply":"2022-03-19T09:18:03.706143Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"product_list = ['Shoes', 'Garment Full body', 'Bags', 'Garment Lower body', 'Underwear/nightwear','Accessories']\ncolors = ['cadetblue', 'orange', 'mediumspringgreen', 'tomato', 'lightseagreen','skyblue']\nk = 0\nsns.set(rc={'axes.facecolor':'#faf0fa'}) # graph facecolor\nfont_color = '#3e0542'\ncsfont = {'fontname':'Georgia'} # title font\nhfont = {'fontname':'Calibri'} # main font\nfig, ax = plt.subplots(3, 2, figsize=(20, 15),facecolor = '#d6b6d5')\n\nfor i in range(3):\n for j in range(2):\n try:\n product = product_list[k]\n articles_for_merge_product = articles_for_merge[articles_for_merge.product_group_name == product_list[k]]\n series_mean = articles_for_merge_product[['t_dat', 'price']].groupby(pd.Grouper(key=\"t_dat\", freq='M')).mean().fillna(0)\n series_std = articles_for_merge_product[['t_dat', 'price']].groupby(pd.Grouper(key=\"t_dat\", freq='M')).std().fillna(0)\n ax[i, j].plot(series_mean, linewidth=4, color=colors[k])\n ax[i, j].fill_between(series_mean.index, (series_mean.values-2*series_std.values).ravel(), \n (series_mean.values+2*series_std.values).ravel(), color=colors[k], alpha=.1)\n ax[i, j].set_title(f'Mean {product_list[k]} price in time',fontsize=12, pad=18, color=font_color, **csfont,fontweight = 'bold')\n ax[i, j].tick_params(axis='x', colors=font_color)\n ax[i, j].tick_params(axis='y', colors=font_color)\n \n k += 1\n except IndexError:\n ax[i, j].set_visible(False)\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:18:06.446747Z","iopub.execute_input":"2022-03-19T09:18:06.446998Z","iopub.status.idle":"2022-03-19T09:18:21.270709Z","shell.execute_reply.started":"2022-03-19T09:18:06.446971Z","shell.execute_reply":"2022-03-19T09:18:21.269894Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Top 5 Articles with maximum price
","metadata":{}},{"cell_type":"code","source":"max_price_ids = transactions[transactions.t_dat==transactions.t_dat.max()].sort_values('price', ascending=False).iloc[:5][['article_id', 'price']]","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:18:29.474773Z","iopub.execute_input":"2022-03-19T09:18:29.475499Z","iopub.status.idle":"2022-03-19T09:18:33.271883Z","shell.execute_reply.started":"2022-03-19T09:18:29.475462Z","shell.execute_reply":"2022-03-19T09:18:33.270800Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"f, ax = plt.subplots(1, 5, figsize=(20,10),facecolor = '#d6b6d5')\ni = 0\nfor _, data in max_price_ids.iterrows():\n desc = articles[articles['article_id'] == data['article_id']]['detail_desc'].iloc[0]\n desc_list = desc.split(' ')\n for j, elem in enumerate(desc_list):\n if j > 0 and j % 5 == 0:\n desc_list[j] = desc_list[j] + '\\n'\n desc = ' '.join(desc_list)\n img = mpimg.imread(f'../input/h-and-m-personalized-fashion-recommendations/images/0{str(data.article_id)[:2]}/0{int(data.article_id)}.jpg')\n ax[i].imshow(img)\n ax[i].set_title(f'price: {data.price:.2f}',fontweight = 'bold')\n ax[i].set_xticks([], [])\n ax[i].set_yticks([], [])\n ax[i].grid(False)\n ax[i].set_xlabel(desc, fontsize=10,fontweight = 'bold')\n i += 1\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:18:36.642074Z","iopub.execute_input":"2022-03-19T09:18:36.642369Z","iopub.status.idle":"2022-03-19T09:18:38.457362Z","shell.execute_reply.started":"2022-03-19T09:18:36.642338Z","shell.execute_reply":"2022-03-19T09:18:38.456593Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Top 5 Articles with minimum price
","metadata":{}},{"cell_type":"code","source":"min_price_ids = transactions[transactions.t_dat==transactions.t_dat.min()].sort_values('price', ascending=True).iloc[:5][['article_id', 'price']]","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:18:47.778970Z","iopub.execute_input":"2022-03-19T09:18:47.779302Z","iopub.status.idle":"2022-03-19T09:18:51.731701Z","shell.execute_reply.started":"2022-03-19T09:18:47.779262Z","shell.execute_reply":"2022-03-19T09:18:51.730958Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"f, ax = plt.subplots(1, 5, figsize=(20,10),facecolor = '#d6b6d5')\ni = 0\nfor _, data in min_price_ids.iterrows():\n desc = articles[articles['article_id'] == data['article_id']]['detail_desc'].iloc[0]\n desc_list = desc.split(' ')\n for j, elem in enumerate(desc_list):\n if j > 0 and j % 4 == 0:\n desc_list[j] = desc_list[j] + '\\n'\n desc = ' '.join(desc_list)\n img = mpimg.imread(f'../input/h-and-m-personalized-fashion-recommendations/images/0{str(data.article_id)[:2]}/0{int(data.article_id)}.jpg')\n ax[i].imshow(img)\n ax[i].set_title(f'price: {data.price:.4f}',fontweight = 'bold')\n ax[i].set_xlabel(desc, fontsize=10,fontweight = 'bold')\n ax[i].set_xticks([], [])\n ax[i].set_yticks([], [])\n ax[i].grid(False)\n i += 1\nplt.axis('off')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-03-19T09:18:53.491856Z","iopub.execute_input":"2022-03-19T09:18:53.492567Z","iopub.status.idle":"2022-03-19T09:18:55.164489Z","shell.execute_reply.started":"2022-03-19T09:18:53.492527Z","shell.execute_reply":"2022-03-19T09:18:55.163149Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#Please check out my notebook on H and M Fashion Recommendation.Click on the link below
","metadata":{}},{"cell_type":"markdown","source":"# https://www.kaggle.com/code/nadianizam/h-m-fashion-recommendation-with-pyspark","metadata":{}},{"cell_type":"markdown","source":"#Please do leave your comments /suggestions and if you like this kernel greatly appreciate to UPVOTE
","metadata":{}}]}